create_pull_request

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

The description discloses the 'never merges it' behavior and the stdin/audit-log behavior, both of which go beyond the schema. Annotations only provide readOnlyHint=false and destructiveHint=false, so the description carries the disclosure burden. The stdin/audit-log note is valuable behavioral context an agent wouldn't otherwise know.

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?

Three sentences, zero filler. Every sentence adds distinct value: purpose/scoping, non-destructive disclaimer, and the stdin/audit-log behavioral note. Front-loaded with the primary purpose in the first sentence.

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?

For a create operation with no output schema and limited annotation coverage, the description covers the key dimensions: what it does, what it doesn't do (no merge), and a security-relevant behavior (audit log). Missing some guidance on draft/maintainerCanModify defaults, but given this is primarily a creation action, the description is largely sufficient.

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 33% (3 of 9 params described: base, head, repository), so the description must compensate but doesn't add any parameter-level detail. However, the description's note about title/body being 'sent through stdin' adds semantic meaning to those parameters beyond what the schema provides, slightly elevating the score.

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 precise verb+resource: 'Create a pull request in an allowed repository.' It also immediately distinguishes the key non-destructive behavior ('This never merges it'), which differentiates it from sibling merge_pull_request. The 'allowed repository' qualifier adds useful scoping context.

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 states what the tool does and that it's restricted to 'allowed repositories,' implying that other repositories are out of scope. However, it doesn't explicitly state when to choose this over the many other PR-related siblings (like update_pull_request or comment_pull_request), nor any exclusions about when NOT to use it beyond the never-merges note.

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