Find frames that look like an image

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description does add genuine behavioral value by revealing that the result mixes two kinds of evidence — visually similar frames and textual passages about the subject — which the annotations don't convey. It stops short of describing match confidence, behavior when nothing matches, or whether matching is against every indexed video by default.

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 economical sentence with no filler, and the core outcome is front-loaded. The fragmentary, verb-less phrasing ('Where a picture... appears: frames that look like it') trades a little clarity for brevity but wastes no space.

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?

An output schema exists, so return-value detail is not the description's burden, and annotations cover the read-only profile. What remains missing is around the edges of invocation: no note on whether all indexed videos are searched by default, and no expectation-setting for zero-match or low-confidence results — modest gaps for a three-parameter 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 100%, with top_k, video_ids and image_path each documented in the schema itself, so the baseline is 3. The description adds no further parameter meaning — it doesn't say how many results are typically useful or that scoping via video_ids exists — so it neither compensates nor detracts.

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 names a concrete outcome — locating where a picture, logo, chart or slide appears — and clarifies the return types (matching frames plus related passages). It is more specific than the bare name, though it never states an explicit verb like 'search' and gives no contrast with siblings such as video_search or video_frames, so an agent must infer that this is a visual-similarity lookup over indexed videos.

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?

There is no when-to-use guidance: no statement of when to pick this over video_search, video_find_phrase or video_frames, and no mention of prerequisites such as the image needing to correspond to indexed content. The use case (finding a logo/chart/slide) is implied by the examples, but routing between alternatives is left entirely to inference.

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