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 covers key behaviors: it returns only summaries with image URLs, is owner-scoped to the account, and defaults to pending candidates. It does not mention ordering, pagination, or explicit read-only status, but for a listing tool the disclosed behaviors are useful and accurate.

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 concise and front-loaded with the main purpose, followed by a behavioral note and a default. All three sentences carry meaningful information and no filler. It uses a dash to separate the core definition from the elaboration, making it efficient, though slightly denser than the bare-minimum style.

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 only two optional parameters and no output schema, the description provides enough context for an agent to call it correctly: it defines candidates, clarifies what is returned, points to the alternative for images, and notes the default filter and account scoping. Minor gaps (e.g., ordering, pagination) are not critical for correct invocation.

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 100% for both parameters, so the baseline is 3. The description adds no new meaning about status or replay_id beyond what the schema already provides; it only restates the default in prose. The schema itself documents the enum values and the replay_id narrowing purpose, so the description is not needed to compensate.

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 a specific verb and resource: 'List AI Visual Review candidates' and defines them as 'flow-replay steps where the perceptual pixel-diff flagged a change against the approved baseline.' It also distinguishes itself from the sibling tool get_visual_review by explicitly noting it returns summaries only and directing users to get_visual_review for images.

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 explicit usage guidance: it names the alternative tool (get_visual_review) for fetching images, explains when to use the replay_id param ('when you were asked to review a particular replay'), and clarifies the default status filter. This tells an agent when to use this tool versus alternatives and reduces the chance of picking the wrong one.

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