GitRanks Contribute

Find issues

find_issues

Read-only

Lists the open-source issues recommended for this contributor, best first, filtered by the input, each saying whether it can be claimed now. Use it to choose an issue to work on. Issues a claim would be refused on (a repository's contributor bar or issue rules, such as good first issues kept for newcomers) are left out. Without a token it answers the day's example issues, the same for everyone, and ignores the filters.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_issues"
  }
}

Input Schema

Name	Required	Description
`mode`	No	GitRanks Learn (invite-only): "learn" lists the issues that fit the contributor's Learn goal and claims one with a lesson to write after the fix (the answer adds lessonBrief)
`repo`	No	Only this repository, as owner/name
`after`	No	The previous page's `next`, for the page after it
`first`	No	Page size, 1 to 20; 10 by default
`kinds`	No	Only issues of these kinds; any kind by default
`topics`	No	Only issues matched on one of these topics: a name as an item's `why` gives it (e.g. react) or a GitHub topic node id; case ignored
`maxSize`	No	The largest estimated size: S, M or L (issues without an estimate are kept); any by default
`languages`	No	Only issues in these languages; any language by default

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real behavioral detail: ineligible issues are filtered out, and without a token it returns the day's example issues that ignore filters. It says nothing about pagination behavior or the response envelope.

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

Conciseness4/5

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

Front-loaded with the core behavior and ordering first, then eligibility, then the unauthenticated caveat. Four sentences, all doing work, though the phrasing is dense enough to require a second read.

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, the description must convey the result shape, and it does: an ordered list with per-item claimability. Pagination and the anonymous-response details are only partly covered (the cursor is left entirely to the schema).

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 baseline is 3; the schema documents every filter, its enum, and the page cursor. The description only adds that filters are ignored in the unauthenticated case, which is useful but marginal beyond the schema.

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 ('Lists the open-source issues recommended for this contributor') plus ordering ('best first') and a per-item field ('whether it can be claimed now'). It is clearly distinguishable from write-side siblings such as claim_issue.

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

Usage Guidelines4/5

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

'Use it to choose an issue to work on' gives clear usage context, and the exclusion of issues a claim would be refused on clarifies scope. It does not explicitly name the follow-up sibling (claim_issue) as the next step, which keeps it short of a 5.

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

All GitRanks Contribute tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.