Judge and rank thumbnails

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

Annotations only declare readOnlyHint and openWorldHint; the description adds the meaningful non-obvious fact that an external vision model provider is required, which implies cost, latency, and a dependency on model configuration. It also discloses the shape of the result (per-image scores 1-4, an ordering, and suggested fixes), though it says nothing about failure modes when the provider is unconfigured.

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 dense sentence with the action and evaluation criteria front-loaded and the prerequisite appended last, which is the right ordering. The parenthetical provider list is slightly listy but earns its place by telling the agent which model backends satisfy the requirement.

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 2-parameter read-only tool with no output schema, the description covers purpose, criteria, result shape, and the key external dependency. The remaining holes are the path/URL ambiguity of image_paths and what happens when no vision model is configured, which are real but modest gaps for a tool this simple.

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% for both parameters, so the description must compensate. 'Scores 1-4 thumbnail images' hints at the array's purpose and its 1-4 sizing, and 'fit with the title' explains what the title parameter is used for, but it never clarifies what image_paths values must be (local paths vs URLs) or the format of the title 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?

Specific verb+resource with the evaluation criteria spelled out (small-size readability, emotion, subject clarity, title fit) plus the output behavior (ranks and lists fixes). It is unmistakably distinct from siblings like generate_thumbnails, set_thumbnail, and extract_frames without needing to name 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?

The only usage-shaped statement is a prerequisite: 'Needs a vision model (Claude, OpenAI, Gemini, Azure).' There is no explicit guidance on when to prefer this over generate_thumbnails, whether it should be run before set_thumbnail, or whether multiple candidate images must come from the same video. Usage must be inferred.

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