Create owner-approved preparation PR

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

Annotations already declare the tool as a non-read-only, open-world, destructive, non-idempotent write. The description adds critical context beyond those: explicit owner approval of a digest is required, the tool never merges or publishes, and on uncertain writes it only reconciles matching PRs rather than retrying blindly. This directly complements the non-idempotent hint and clarifies scope.

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?

The description is three efficient sentences with no wasted words. The front-loading is slightly off because it opens with a prerequisite rather than the core action, but the action follows immediately and the overall structure is clear and compact.

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?

Given the tool is a destructive, open-world, non-idempotent write with annotations covering the safety profile, the description adds the key approval requirement, the no-merge/no-publish scope, and the reconciliation behavior. The main gap is the lack of explanation for preparation_id and no output schema, but overall it provides enough context for an agent to decide and invoke.

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 0%, so the description must carry parameter meaning. It explains approved_digest (must be the exact displayed patch digest) and authorize_pull_request (explicit owner approval), but leaves preparation_id unexplained and provides no format hints. This partial coverage is adequate but not complete.

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 (creates) and resources (branch and PR) in the source repository, making the action clear. It does not explicitly name sibling tools or explain how this differs from prepare_repository or create_launch, but the core purpose is unambiguous.

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?

It implies usage by specifying prerequisites (owner approval of the exact patch digest) and constraints (never merges or publishes; reconcile only on uncertain writes). However, it does not explicitly state when to use this tool versus alternatives like prepare_repository or get_repository_preparation.

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