tool-design

tool-design is a cursor rule for Cursor from sijeeshmiziha/visionagent. It costs 676 tokens per session, scanned A, original, MIT.

A set of design rules for tools used by AI agents. It covers clear purposes, typed inputs, minimal tool collections, consistent names, and results that avoid unnecessary context.

In plain words
What is it for?
Use it when designing or reviewing agent tools, APIs, tool descriptions, parameters, and tool-result formats.
Why use it?
It helps prevent agents from choosing between overlapping tools or receiving confusing, oversized outputs.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/sijeeshmiziha/visionagent/tool-design
Clone the repo
git clone --depth 1 https://github.com/sijeeshmiziha/visionagent

Made for: Cursor.

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 tool-design

README.md
[![agentmods](https://agentmods.dev/badge/rules/sijeeshmiziha/visionagent/tool-design.svg)](https://agentmods.dev/rules/sijeeshmiziha/visionagent/tool-design)
Your own site
<a href="https://agentmods.dev/rules/sijeeshmiziha/visionagent/tool-design"><img src="https://agentmods.dev/badge/rules/sijeeshmiziha/visionagent/tool-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 676 This file is loaded in full into every session.
When invoked 676 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00676 $0.00676
Opus 5 $0.00338 $0.00338
Sonnet 5 $0.00135 $0.00135
Haiku 4.5 $0.00068 $0.00068

Measured 3d ago against content hash 0fc66b46ae0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d ago.

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.

.cursor/rules/tool-design.mdc · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool Design for Agents

Self-Contained Tools

  • Each tool: single clear purpose, robust to errors, unambiguous description and parameters.
  • Use descriptive, typed inputs (e.g. Zod schemas); avoid overlapping or ambiguous tool contracts.

Minimal Tool Sets / Choosing the Right Tools

  • Keep the tool set minimal. No bloated or overlapping tools; if a human can’t choose which tool to use, the agent can’t either.
  • Agents have limited context; prefer tools that match how agents work (e.g. search_contacts over list_all_contacts).
  • Build a few workflow-oriented tools for high-impact tasks; avoid wrapping every API endpoint.
  • Consolidate: e.g. schedule_event (find availability + schedule) instead of list_users + list_events + create_event; search_logs instead of read_logs; get_customer_context instead of separate get/list tools. Each tool should subdivide tasks like a human would and reduce context from intermediate outputs.

Namespacing

  • Use consistent prefixes or suffixes (e.g. by service: asana_search, jira_search; by resource: asana_projects_search, asana_users_search) so agents can select the right tool. Naming can affect evaluations; try prefix vs suffix in your own evals.

Returning Meaningful Context

  • Prefer high-signal, human-interpretable fields (e.g. name, file_type) over low-level ones (uuid, mime_type).
  • Resolve opaque IDs to semantic labels or simple schemes (e.g. 0-indexed) to reduce retrieval hallucinations.
  • Optional response_format (e.g. concise vs detailed) so the agent can request less context when IDs aren’t needed.

Token-Efficient Results

  • Return minimal, relevant data; filter, aggregate, or transform before returning. Prefer summaries or slices over full dumps.
  • Add pagination, range selection, filtering, or truncation with sensible defaults; cap response size where appropriate.
  • Truncation messages should steer the agent (e.g. “use smaller or more targeted searches”).
  • Error responses: give specific, actionable guidance and valid examples—not opaque codes or raw tracebacks.

Read the full file on GitHub · 49 lines

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. 3d ago First seen · 49 lines · 676 tokens per session scan A 0fc66b46ae0c

Subscribe to this mod's changes

tool-design is a cursor rule published in the GitHub repository sijeeshmiziha/visionagent (2 stars, last pushed 5mo ago), licensed MIT. It adds 676 tokens to every session, about $0.0034 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.