Get Pull Requests

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

Annotations only give readOnlyHint, and the description confirms 'Read-only' while adding substantial non-obvious behavior: null/runCount semantics, the distinction between 'no runs' and a failed lookup, the {status:'unavailable'} sentinel with an instruction never to report 'no runs', and a prompt-injection warning about PR titles. This is far beyond what the annotation conveys.

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?

Front-loaded with the core purpose, then mode-specific behavior, then edge-case semantics. Dense but nearly every clause carries actionable information; the prompt-injection warning is justified given PR titles are user-controlled, though the text is close to the upper bound of comfortable length.

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?

With no output schema, the description carries the return-shape burden and does so: it names the fields returned in both list mode (status, author, latest test run) and detail mode (branches, merge state, size, latest test runs), and explains the failure sentinels. Nothing an agent needs to call this correctly is missing.

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?

Schema coverage is 100%, so baseline is 3, but the description adds real disambiguation: pr_id is the `prId` from the list and explicitly 'not the PR number', which the schema alone only hints at via the example format. The 20-PR cap and default listing behavior are also stated, though limit/status semantics stay in the schema.

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?

States a specific verb+resource ('Pull requests of the project's connected GitHub/GitLab repo') and splits into two clearly distinct modes (list vs. single-PR detail). An agent can tell exactly what comes back in each mode without opening the schema.

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?

Explicitly says to omit pr_id to list and to pass a pr_id for detail, plus a concrete recovery path: when latestRun is null, 'call again with its pr_id' for a definite answer. It also explains when the list may be short (syncing: true). No sibling tool overlaps this resource, so no alternative-tool routing is needed.

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