Fetch a CI/CD pipeline run's jobs and artifacts

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It discloses key behaviors: the resolution logic (runId vs. latest failed run), the output (jobs and artifacts), and a significant restriction (allowedRepos config requirement, referencing guardrails.ts). It does not mention whether the operation is read-only, but 'lists' implies no side effects. The description adds context beyond a bare schema, covering important operational constraints, though it could go further (e.g., error handling or rate limits).

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

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

The description is two concise sentences, front-loaded with the main purpose in the first sentence and the key prerequisite in the second. Every phrase earns its place—no fluff or redundancy. It is appropriately sized for the tool's complexity.

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

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

The description covers the essential aspects for an agent to use this tool: what it does (fetch jobs/artifacts), how it selects the run (runId or latest failed on branch), and a critical prerequisite (allowedRepos config). Since there is no output schema, the description directly states the return content ('jobs and artifacts'), which is sufficient. It lacks some detail like error cases or return format specifics, but given the moderate complexity and clear title, it is reasonably complete.

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

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

The input schema already provides 100% coverage, describing all four parameters (owner, repo, runId, branch) with examples and defaults. The tool description itself adds no additional parameter-specific information; it only mentions runId and branch conceptually, but the schema already explains them. Per the rubric, this is a baseline 3 since the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose: 'Resolves a GitHub Actions run (by runId, or the most recent failed run on a branch) and lists its jobs and artifacts.' This is specific with a verb ('Resolves', 'lists'), a resource (GitHub Actions run), and outputs (jobs/artifacts). It also distinguishes itself from sibling tools (e.g., extract_failure_signal, find_similar_past_failures) which focus on analyzing or recording triage, not fetching raw run data.

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

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

The description provides clear functional context: it fetches a run's jobs and artifacts, with an explicit resolution mode ('by runId, or the most recent failed run on a branch'). It also mentions a critical prerequisite: 'Only works for repos listed in allowedRepos in ~/.ci-triage-mcp/config.json -- add a repo there yourself first.' While it does not explicitly name alternative tools or say 'use this when...', the purpose is clear enough for an agent to infer when to use it, and the prerequisite offers important usage guidance.

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