Skip to main content
Glama
github-fetcher

github-fetcher

by KurvCygnus

GitHub user repositories

github_user_repos
Read-onlyIdempotent

List a GitHub user's public repositories with star, fork, language, and push-time details; filter forks or minimum stars and rank by stars to find relevant projects.

Instructions

List a user's public repositories with the house projection: visibility, fork status, stars, watchers, language, push time, and description; type defaults to owner. Forks are dropped by default (include_forks: true keeps them) and min_stars keeps repositories at or above the star floor; both filters are client-side, so a filtered page can come back short. sort: stars gathers up to 10 pages of 100 client-side, ranks by stars descending, and reports has_more/next_page from the filtered window with gather_truncated when the cap stopped the gather. Costs 1 core call, up to 10 with sort: stars. Returns {items[{name, full_name, private, visibility, fork, stars, watchers, language, pushed_at, description, html_url}], page, per_page, has_more, next_page, gather_truncated}.

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": {
      "user": "<user>"
    },
    "name": "github_user_repos"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, starting at 1
sortNoSort field: created, updated, pushed, full_name, or stars (stars ranks client-side)
typeNoFilter by relationship to the user: all, owner, public, private, or member
userYesGitHub user login, like octocat (alphanumerics and hyphens)
freshNoBypass the local cache
orderNoSort order: asc or desc (ignored with sort: stars)
per_pageNoItems per page, 1-100, default 20
min_starsNoKeep repositories with at least this many stars (client-side filter)
include_forksNoKeep fork repositories in the results; defaults to false, pass true to include them

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • changedInput schema / properties / order / description
      Previous value: -"Sort order: asc or desc"New value: +"Sort order: asc or desc (ignored with sort: stars)"
  2. Addedv0.3.0

TDQS

A4/5.0
Behavior4/5

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

Goes well past the readOnly/idempotent annotations by disclosing the cost model ('1 core call, up to 10 with sort: stars'), that filters are client-side so pages can return short, and that sort: stars paginates a client-side gather and can terminate early with gather_truncated. It does not explain the caching behavior implied by the 'fresh' parameter or any auth requirements, leaving a small gap for a read tool with these annotations.

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

Conciseness3/5

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

Dense and front-loaded, ordering purpose, then filtering caveats, then sort cost, then return shape. However the projected field list is enumerated twice (in the opening clause and again inside the returns block), which is wasted space in an already long single paragraph and makes the sentence hard to scan.

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

Completeness4/5

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

With no output schema and 9 parameters, the description carries the return contract itself and does so, listing the item fields and pagination flags (has_more, next_page, gather_truncated). The main omissions are cache behavior behind 'fresh' and any statement about total counts or empty-result shape, which are minor for a read-only list tool.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains the consequence of the client-side filters (a filtered page can come back short) and how the sort: stars gather reports has_more/next_page from the filtered window rather than the raw response. 'type defaults to owner' also resolves an ambiguity the enum alone does not.

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?

States a specific verb and resource ('List a user's public repositories') plus the exact projection returned (visibility, fork, stars, watchers, language, pushed_at, description) and the default relationship filter ('type defaults to owner'). That scoping to a single user's repos, with a fixed house projection, is enough for an agent to tell it apart from repo-search or repo-detail siblings without opening a schema.

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

Usage Guidelines3/5

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

Gives useful conditional guidance inside the tool (defaults to owner, forks dropped unless include_forks: true, sort: stars costs up to 10 calls instead of 1), which implicitly tells the agent when the expensive path is warranted. It never names an alternative tool or says when NOT to use this one, so routing between this and the search/repo siblings is still inferred.

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