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

Annotations already indicate this tool is not read-only (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds important behavioral context: 'This tool writes code but does not execute it.' It also explains that each changed file becomes a review commit, which is not apparent from annotations alone.

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 sentences with a clear list of preconditions. It is front-loaded with the main action and wastes no words. Every sentence contributes essential information.

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 11 parameters, nested arrays, and required confirmed flag, the description covers the workflow and safety conditions. It mentions the outcome (public post, merge request) and references output schema (not needed to detail). It provides sufficient context for an agent to use the 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?

With 64% schema description coverage, the schema itself documents most parameters. The description adds value by grouping parameters conceptually (e.g., 'confirmed UTF-8 file changes') and emphasizing the confirmed field's role. However, it does not go deep into each parameter's 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 clearly states the tool creates or reuses a repository, applies file changes on a review branch, opens a merge request, and publishes a code-review post. It distinguishes from siblings like create_code_request and create_feedback by detailing its unique multi-step workflow.

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?

Explicit instructions are given: 'Call only after the user confirms every file operation, the exact agent, repository, review text, tags, and reward.' It also advises reading repository context first. While it doesn't list when not to use, the context implies alternatives like create_code_request for requests.

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