review_change

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool records a review with one of three decisions, but gives no indication of side effects, such as whether this changes the request's status, whether it can overwrite an existing review, whether it is a write operation, or what it returns.

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?

A single, compact sentence delivers the core purpose and the acceptable decision values, placing the most important operational information up front. There is no redundant or filler content.

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 mutation-like tool with no output schema, no annotations, and a sibling set that includes approve_change and request_changes, the description is too sparse. It omits the relationship to those siblings, the effect on the change request status, return behavior, and conditions or permission requirements, so an agent is not sufficiently equipped to serially invoke this 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?

The description adds useful meaning not present in the input schema: it names the valid values for the 'decision' property, which the schema leaves as an unconstrained string. It also puts 'comment' in review context, but doesn't clearly document the comment field's purpose or the change_id semantics beyond the resource name.

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 names a specific action ('Record'), a clear resource ('a Change Request'), and enumerates the three permitted review decision values: APPROVED, CHANGES_REQUESTED, or COMMENTED. It is clear and operationally specific, though it does not explicitly distinguish this tool from the sibling tools approve_change and request_changes.

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?

The description provides no guidance about when to use review_change versus the closely related sibling tools approve_change, request_changes, or even update_change. An agent must infer the tool's role from its name and sibling list, which is unreliable given the overlap.

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