match-reference

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

With no annotations, the description carries the full burden, and it provides useful behavioral details: it renders the current frame, returns a side-by-side and a difference map, and explains that the difference map is bright where they differ. It does not disclose whether the operation is non-destructive or what happens with invalid reference paths, but it does not contradict annotations and offers more than a minimal description.

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 efficient, with two sentences that are front-loaded with the primary verb and resource. It packs meaningful details (rendering, output types, difference map interpretation, and comp selection) into a compact space without redundant or verbose wording.

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 that there is no output schema, the description sufficiently explains what the tool returns and how to specify inputs, allowing an agent to invoke it confidently. It could additionally mention the time parameter or error handling, but those are at least partially covered by the input schema, so the overall completeness is high.

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 schema covers 100% of parameters with descriptive text, so the baseline is 3. The description does not add new meaning beyond what the schema provides—it only restates the comp selection rule and the need for an on-disk path, both already in the schema. No additional parameter semantics are introduced.

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 opens with a specific verb+resource phrase, 'Compare a composition against a reference image,' and clearly distinguishes the tool from siblings like see-frame or contact-sheet. It further details the two outputs (side-by-side and difference map) and explains the purpose of seeing exactly where the render deviates.

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 clearly implies when to use this tool: when you need to compare a composition against a reference and converge on a match. It does not explicitly name alternatives or exclusions, but within the context of sibling tools this is the only comparison-focused tool, making the usage clear.

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