Skip to main content
Glama
github-fetcher

github-fetcher

by KurvCygnus

GitHub commit

github_commit
Read-onlyIdempotent

Read a single GitHub commit's message, author, date, line changes, and changed files with bounded patches to inspect one commit in full.

Instructions

Read one commit: message, author, additions/deletions, and the changed files with bounded patches. github_commits lists commits; this reads one in full. Costs 1 core call. Returns {repo, sha, author, date, message, additions, deletions, files, files_truncated, meta}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "repo": "<repo>"
    },
    "name": "github_commit"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoCommit sha, branch, or tag; defaults to the pinned ref when one exists, otherwise the repository default branch
repoYesRepository in owner/name form
freshNoBypass the local cache

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description adds genuinely new context: quota cost per call, bounded patch sizes, and a files_truncated flag signalling partial results. It does not mention the local cache or what the fresh parameter bypasses, which is the main remaining behavioral gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short, front-loaded clauses: what it reads, how it differs from the sibling, cost, and return shape. Nothing is redundant and the return-field enumeration replaces the missing output schema efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema available, the description compensates by listing the returned keys including files_truncated and meta, and it discloses call cost and truncation risk. For a three-parameter read tool whose annotations carry the safety profile, an agent has everything needed to call it correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so repo, ref, and fresh are already fully documented in the schema, including the default-ref fallback logic. The description adds no further parameter semantics beyond a passing reference to patch bounding, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource — 'Read one commit' — and enumerates exactly what is returned (message, author, additions/deletions, changed files with patches). It also explicitly contrasts itself with the sibling github_commits, so an agent can distinguish the single-read tool from the list tool without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names the alternative (github_commits) and the condition that selects it ('lists commits; this reads one in full'), which is the exact routing decision an agent faces. The cost note ('Costs 1 core call') further supports a use/don't-use judgement when budget matters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.