List reviews

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

Goes far beyond the readOnlyHint annotation by disclosing ordering, the ref-vs-commit interpretation, guiUrl behavior regardless of whether GitWarren is running, token/cookie behavior after restarts, and the tailnet conditions for webUrl. This gives the agent concrete expectations for results and failure modes. No contradiction with the annotations.

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 main action and filtering are front-loaded and paragraphs separate core behavior from link guidance. However, the description is quite long for a two-optional-parameter list tool; the token/cookie troubleshooting and tailnet scenarios are detailed enough that not every sentence earns its place.

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?

Even without an output schema, the description tells the agent what results contain (guiUrl, conditional webUrl), how to present them, and how the review object should be understood. It also covers edge cases like a refused connection and restart-token behavior, so the tool can be invoked and interpreted without additional assumptions.

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 description coverage is 0%, so the description must carry the parameter meaning. It explains that repositoryId and status can be combined, that status is 'open' or 'closed', and that omitting both yields all reviews. It does not say where repositoryId comes from, such as list_repositories, but the core filtering semantics are clear.

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?

States exactly what the tool does: lists reviews with newest activity first, with explicit filtering by repositoryId and/or status. It also clarifies the scope ('list every review across all tracked repositories') and distinguishes the review object's semantics from commit-level details, so an agent can tell it apart from get_review.

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?

Provides clear invocation context: use filters when targeting a subset, omit both to list everything, and use git when actual changed content is needed. It does not explicitly name sibling alternatives such as get_review for single-review lookups, so it stops short of full when-not guidance.

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