askell-mcp: Skill for Claude Code

.agents/skills/mcp-tool-design/SKILL.md

mcp-tool-design is a skill for Claude Code, Codex from Neschadin/askell-mcp. It costs 47 tokens per session (696 once invoked), scanned A, original, MIT.

A guide for designing tools that AI agents can find, understand, combine, and use reliably through MCP. MCP is a protocol for connecting agents to tools and data.

In plain words
What is it for?
Use it to decide which API functions should become tools, design their names and inputs, add pagination and filtering, describe errors, and build evaluation tests.
Why use it?
It helps avoid tools with confusing names, poorly shaped inputs, incomplete results, or unclear errors, and includes ways to test whether agents can complete real tasks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Neschadin/askell-mcp's own configuration. It tells Claude Code and Codex how to work on askell-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything askell-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Neschadin/askell-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Neschadin/askell-mcp/main/.agents/skills/mcp-tool-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Neschadin/askell-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-tool-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/neschadin/askell-mcp/mcp-tool-design/github.svg)](https://agentmods.dev/skills/neschadin/askell-mcp/mcp-tool-design)
Your own site
<a href="https://agentmods.dev/skills/neschadin/askell-mcp/mcp-tool-design"><img src="https://agentmods.dev/badge/skills/neschadin/askell-mcp/mcp-tool-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-tool-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/neschadin/askell-mcp/mcp-tool-design"><img src="https://agentmods.dev/badge/skills/neschadin/askell-mcp/mcp-tool-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 696 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00696
Opus 5 $0.00023 $0.00348
Sonnet 5 $0.00009 $0.00139
Haiku 4.5 $0.00005 $0.00070

Measured 9d ago against content hash 6004b0d70b11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-tool-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/connections.py, scripts/evaluation.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/mcp-tool-design/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Design & Evaluation

Design MCP tools that LLMs can discover, compose, and use reliably. For project scaffolding, SDK v2 patterns, and transport setup, use the typescript-mcp-server-generator skill.

When to Use

  • Choosing which API endpoints become tools vs higher-level workflows
  • Naming tools, shaping inputs/outputs, and writing descriptions agents can act on
  • Adding tool annotations (readOnlyHint, destructiveHint, etc.)
  • Building evaluation suites to verify agents can solve real tasks with your tools

Tool Design

API Coverage vs Workflow Tools

Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools are convenient for specific tasks; broad coverage lets agents compose operations. When uncertain, prioritize comprehensive API coverage.

Naming and Discoverability

Use consistent, action-oriented prefixes (github_create_issue, github_list_repos). Names should make the tool's purpose obvious without reading the full description.

Context Management

Return focused, relevant data. Support pagination and filtering where the backing API allows. Concise descriptions beat exhaustive parameter dumps.

Error Messages

Errors should guide agents toward a fix — include what failed, why, and a concrete next step (retry with different params, call another tool first, etc.).

Tool Annotations

Set hints so clients can surface appropriate UX:

  • readOnlyHint — no side effects
  • destructiveHint — irreversible or high-impact changes
  • idempotentHint — safe to retry
  • openWorldHint — interacts with external/unbounded data

Planning Checklist

Before implementing, review the service API docs for endpoints, auth, and data models. List tools to implement starting with the most common read operations, then writes.


Evaluation Suite

After tools are implemented, verify agents can use them effectively.

Load Evaluation Guide for the full process and runner scripts.

Read the full file on GitHub · 94 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 94 lines · 47 tokens per session scan A 6004b0d70b11

Subscribe to this mod's changes

mcp-tool-design is a skill published in the GitHub repository Neschadin/askell-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 696 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens

telnyx-messaging-hosted-curl

Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens