rosetta mcp-tool-descriptions.instructions.md

rosetta mcp-tool-descriptions.instructions.md is an instructions file for GitHub Copilot from tikoci/rosetta. It costs 133 tokens per session, scanned A, original, MIT.

Guidance for writing descriptions of MCP tools, which are tools that let an agent interact with external data or services. It covers workflows, limits, empty results, and how much related information to return.

In plain words
What is it for?
Use it when documenting tool inputs and outputs, search follow-ups, version limits, and result-size controls.
Why use it?
It helps agents understand what to do next and makes tool responses useful when searches return nothing or when information has important boundaries.

Instructions file for GitHub Copilot

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 instructions/tikoci/rosetta/mcp-tool-descriptions
Clone the repo
git clone --depth 1 https://github.com/tikoci/rosetta

Made for: GitHub Copilot.

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 rosetta mcp-tool-descriptions.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tikoci/rosetta/mcp-tool-descriptions.svg)](https://agentmods.dev/instructions/tikoci/rosetta/mcp-tool-descriptions)
Your own site
<a href="https://agentmods.dev/instructions/tikoci/rosetta/mcp-tool-descriptions"><img src="https://agentmods.dev/badge/instructions/tikoci/rosetta/mcp-tool-descriptions.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 This file is loaded in full into every session.
When invoked 133 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 $0.00133 $0.00133
Opus 5 $0.00067 $0.00067
Sonnet 5 $0.00027 $0.00027
Haiku 4.5 $0.00013 $0.00013

Measured 5d ago against content hash 33de070e4a9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rosetta mcp-tool-descriptions.instructions.md 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 5d 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.

.github/instructions/mcp-tool-descriptions.instructions.md · 13 lines

What it actually says

MCP tool descriptions

Tool descriptions are part of the interface.

  • Include knowledge boundaries when they matter (export date, supported versions, v6 caveats).
  • Use workflow arrows (→ next tool) to guide follow-up calls.
  • Return actionable empty-result hints instead of bare empties.
  • Preserve the relatedCaps(limit) "hunger knob" pattern when expanding routeros_search.
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. 5d ago First seen · 13 lines · 133 tokens per session scan A 33de070e4a9a

Subscribe to this mod's changes

rosetta mcp-tool-descriptions.instructions.md is an instructions file published in the GitHub repository tikoci/rosetta (43 stars, last pushed 19d ago), licensed MIT. It adds 133 tokens to every session, about $0.0007 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 2026-08-30.

Related

Other instructions, from other repositories