Skip to main content
Glama

search_issues

Read-only

Find issues by keyword across all repositories or one repo, filtering by open, closed, or all states. Use when searching issue titles and bodies rather than code, repositories, or pull requests.

Instructions

Full-text search over issues (not code, not repos, not pull requests) across ALL of the user's repositories, or one repo if given. Supports open or closed state. Use when the question has a keyword ('issues mentioning auth'), asks about CLOSED issues, or spans every repo. Do NOT use to list a repo's open issues with no keyword (use list_open_issues) or to find repositories (use list_repositories).

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": "search_issues"
  }
}

Input Schema

NameRequiredDescriptionDefault
repoNoRepository as 'owner/name' (e.g. 'octocat/hello-world'). A bare name like 'hello-world' is resolved against the authenticated user's account.
limitNoMaximum number of items to return (1-50). Totals are reported separately, so a small limit is fine when only a count is needed.
queryNoOptional keywords to match in issue titles and bodies, e.g. 'login timeout'. Omit to match every issue in scope (e.g. all closed issues).
stateNo'open', 'closed' or 'all'. Default 'all'.all

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and breadth are covered structurally; the description reinforces this by spelling out the cross-repo search scope and the content types it will not touch. It does not discuss result shape, totals, or any rate-limit/pagination behavior, which is the remaining gap for a search tool.

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?

Three tight sentences: scope first, capabilities second, routing constraints last. Parenthetical exclusions are dense but each clause carries decision-relevant information and nothing is repeated from the schema verbatim.

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?

For a 4-parameter, all-optional search tool with full schema coverage and no output schema, the description covers scope, filters, and sibling routing adequately. It leaves the return shape and total-count reporting to the schema rather than describing them, a minor omission given no output schema exists.

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%, and every parameter (repo format, limit range, query semantics, state enum) is already documented in the schema. The description restates the repo scoping and state support but adds no format or edge-case detail beyond it, so the baseline of 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?

States a specific verb and resource ('Full-text search over issues') together with an explicit scope ('across ALL of the user's repositories, or one repo if given') and parenthetical exclusions ('not code, not repos, not pull requests'). An agent can separate this from list_open_issues or list_repositories without opening any 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?

Gives concrete selection criteria ('keyword', 'asks about CLOSED issues', 'spans every repo') and explicit negative routing with the sibling to use instead ('Do NOT use to list a repo's open issues with no keyword (use list_open_issues)', 'use list_repositories'). Both the when and the when-not are present with named alternatives.

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