review_image

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

With no annotations, the description carries the full burden. It does disclose that output is a set of warnings and that each warning points to the fixing tool, plus an indirect state note ('Not done while it warns'). But it omits permissions, cost, whether it mutates the document, and what the review actually 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?

Short and front-loaded with the check description, which is good. However the trailing 'Not done while it warns' is cryptic and the ellipsis leaves the issue list open-ended, adding ambiguity rather than economy.

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 diagnostic tool with no annotations, no output schema, and an undocumented parameter, the description conveys what is checked and that warnings name fixers, but leaves the return shape, the project parameter, and the meaning of the final sentence unexplained.

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?

There is one parameter ('project') with 0% schema description coverage, and the description says nothing about it or whether omitting it targets the active project. For low schema coverage the description is expected to compensate, and it does not.

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 a specific verb (check) and resource (the document) and enumerates the concrete issues it looks for: off-canvas/low-contrast text, layers outside, blown highlights, upscaled images. The purpose is distinguishable from sibling analysis tools like analyze_image or describe_image, though it doesn't explicitly contrast itself with them.

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?

No statement of when to reach for this tool versus siblings like analyze_image or preview. The clause 'each warning names the tool that fixes it' hints at a remediation workflow but gives no explicit when/when-not condition, and 'Not done while it warns' is too opaque to count as guidance.

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