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

The annotations already signal read-only and idempotent behavior, and the description adds substantial context: it counts from team repositories rather than the member list, includes non-members, reports unmatched_repositories instead of silently counting zero, and counts opened by provider-recorded time. It also discloses that the human-vs-bot split is always reported even when include_bots is false.

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?

Although longer than typical, the description is well-structured and front-loaded: a one-sentence summary, then when-to-use guidance, then counting semantics, then the merged-PR caveat. Every paragraph earns its place and helps the agent avoid real mistakes.

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 all parameters documented in the schema and an output schema available, the description supplies the missing context: which authors are counted, how scoping works, what happens with unmatched repository slugs, and how opened differs from merged. An agent has everything needed to select and invoke this tool 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?

The input schema covers all three parameters with full descriptions, including defaults and repository slug matching, so the schema is doing the heavy lifting. The description reinforces that repositories is the exact source list and mentions unmatched_repositories, but it does not add substantial parameter-level meaning beyond 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?

The description opens with a specific action: Count pull requests OPENED over a recent window, then adds the key breakdown dimensions: per repository, per author, and human-vs-bot/dependabot split. It also distinguishes itself from get-merged-pull-requests by explicitly saying opened is a different set from merged, and from per-person activity tools by explaining what each approach counts.

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 gives explicit trigger questions such as how many pull requests were created, opened or raised, and contexts like today, this week, on a repo, or across the team. It tells the agent when to prefer this over a per-person activity breakdown and names get-merged-pull-requests as the alternative for merges, adding that the two should never be presented as reconciling.

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