Update review

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

The description goes far beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false). It explains validation behavior ('New refs are validated exactly as they are on creation'), the mandatory presence of at least one field, and, most notably, the detailed behavior of the returned guiUrl and webUrl links, including how to handle a user reporting a refused connection and the token/cookie mechanism. This is rich behavioral disclosure that helps the agent understand side effects and interpretation of results.

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 structured in two paragraphs, front-loaded with the core purpose and requirement, then diving into link behavior. While it is somewhat long, every sentence adds value—especially the link explanations, which are crucial for correct agent behavior. There is no redundancy, and the structure logically separates the action from the result handling. It is appropriately detailed without being verbose.

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 tool with 6 parameters, no output schema, but informative annotations, the description covers the essential aspects: what can be updated, the requirement for at least one field, validation, and the detailed semantics of the returned links (guiUrl and webUrl), including how to present them and how to troubleshoot a broken link. This is sufficient for an agent to invoke the tool correctly and interpret its result. The absence of an output schema is mitigated by the thorough explanation of the link behavior.

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 compensate. It names the modifiable fields ('title, description or endpoints') and status, and clarifies that at least one must be provided. It also mentions validation for refs. However, it does not individually explain parameters like id, baseRef, headRef, or description beyond their types in the schema. The description adds some meaning but does not fully document each parameter's semantics, leaving gaps for an agent trying to construct valid input.

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 clear purpose: 'Change a review's title, description or endpoints, or set its status to closed or open again.' It explicitly lists the mutable fields and the status option, distinguishing it from sibling tools like create_review, remove_review, and get_review. The verb 'change' and resource 'review' are specific and 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 provides a clear usage requirement: 'Provide at least one field.' It also explains when to offer guiUrl vs webUrl, which guides post-update behavior. However, it does not explicitly state when to use this tool versus alternatives (e.g., create_review for new reviews), though the context of updating an existing review is implied by the tool name and sibling list. The guidance is adequate but not exhaustive.

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