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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description usefully adds that single-PR mode returns an enriched payload (reviews, checks, mergeability, changed files with diffs), which hints at cost/volume, but it gives no warning about payload size or rate limits when diffs are included.

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 that packs the list mode, the filter values, and the full single-PR return scope with no filler.

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-value burden: it describes single-PR output well but says nothing about what a listing returns or how 'limit' behaves. Those gaps matter for an agent deciding between the two modes.

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 only 25% (only 'repo' is documented), so the description must compensate. It does clarify 'state' (open/closed/all) and 'number' (single PR), but 'limit' is left entirely undefined in both schema and description.

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?

A specific verb (List) plus resource (pull requests), with the two operating modes spelled out: filtered listing vs. single PR by number. This naturally separates it from gh_pull_create and gh_pull_merge, though no sibling is named explicitly.

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 implies usage by explaining that 'state' drives listing and 'number' selects a single PR, but it never says when to prefer gh_pulls over gh_issues, gh_actions, or gh_read, nor any exclusions or prerequisites.

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