update_pull_request

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

Discloses PATCH behavior, state transition effects, label replacement risk, and base retargeting irreversibility. No annotations provided, so description carries full burden and meets it.

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?

Two dense, front-loaded sentences with zero waste. Every sentence provides critical guidance.

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?

Covers key behaviors and risks for all 11 parameters, but does not describe return value format. Minor gap given high complexity.

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?

Adds significant context beyond 100% schema coverage: explains labels replacement semantics, state meaning, and base retargeting risk.

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?

Clearly states the tool updates a single pull request by index using PATCH semantics. Distinguishes from sibling merge_pull_request by clarifying state change without merging.

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 tells when to use alternatives (add_issue_labels/remove_issue_label) for single label changes, and warns about base retargeting rarely reversible.

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