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

Annotations already signal readOnlyHint and openWorldHint, so the description correctly builds on them by explaining the return payload and the practical use of the depth map. It adds behavioral detail beyond annotations by describing downloadable URLs and the intended downstream pipeline usage, though it does not mention zero-result behavior or relevance ranking.

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 front-loaded with the search purpose and compacts a useful amount of return-value detail into one sentence. It is slightly long and run-on, but every clause earns its place by clarifying URLs or downstream usage, so it remains efficient and readable.

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?

With no output schema, the description carries the burden of explaining return values, and it does so thoroughly by enumerating metadata, preview thumbnail, full-resolution URL, depth map, and FrameThrower link. It omits minor invocation details such as result count defaults and relevance sorting, but those are secondary for a read-only search tool.

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 50%, with only query documented. The description enriches query semantics by enumerating searchable dimensions, adding meaning beyond the basic natural-language example. The limit parameter is not addressed in the description, but its schema constraints (1–40) make its behavior reasonably inferable.

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 states a specific action ('Search'), a specific resource ('FrameThrower cinematography reference library'), and the dimensions of search ('concept, mood, color, composition, or scene'). It clearly differentiates itself from siblings by describing a general natural-language search rather than craft-specific lookup, similarity matching, or detail retrieval.

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 conveys when to use it implicitly by listing supported search dimensions, but it does not explicitly mention alternative tools or exclusion criteria. Sibling names like find_similar and find_by_craft suggest boundaries, but the description itself does not guide an agent toward choosing this tool over them.

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