list_pull_requests

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

With no annotations, the description carries the full burden, but 'List pull requests in a GitHub repository' merely restates the operation without behavioral detail. It does not disclose that state defaults to 'open' (so only open PRs are returned by default), that sort/direction controls ordering, or that per_page defaults to 15 with pagination implications.

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?

A single front-loaded sentence with zero wasted words—highly skimmable. The brevity is not the issue; the absence of substance is, and that is penalized elsewhere. For what it attempts, the structure is appropriate and efficient.

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?

Even though an output schema exists, the tool has 7 parameters, no annotations, and 0% schema description coverage. An agent cannot correctly set state values could not know what value... cannot infer that state defaults to 'open' or which sort/direction values are valid, nor can it distinguish this from list_issues. The description is only complete at the level of naming the capability, not at the level of invoking it correctly.

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 description coverage is 0%, and the description adds nothing about the parameters. It only clarifies that owner and repo identify the repository, but the meaning and valid values of state, sort, direction, per_page, and base are entirely undocumented in both the schema and the description. The 0% coverage demands compensation that never comes.

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 states a specific verb ('List') and a specific resource ('pull requests in a GitHub repository'), making the core function clear. However, it does not differentiate from sibling tools like get_pull_request (which fetches a single PR) or list_issues (which in GitHub's API can also return PRs), leaving that inference to the agent.

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?

No when-to-use or when-not-to-use guidance is provided. There is a meaningful overlap with sibling tools—particularly list_issues, since GitHub treats pull requests as issues under the hood—and the description does not clarify when this tool is preferred. It also does not mention that get_pull_request exists for retrieving a single PR.

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