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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds behavioral detail: it 'returns the project identity with its result', 'scans all tiles in parallel', and produces 'coarse SOURCE timestamps' – useful expectations not implied by the schema. It also frames the query as naming 'one concrete visible event', clarifying the semantic requirement. No contradiction with annotations; the description enriches beyond them.

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 dense but front-loaded with key markers 'PROJECT-SCOPED' and 'READ'. Every sentence adds value: scope, behavior, usage, output, and verification steps. It is slightly long but not wasteful; the use of caps and semicolons aids scanning. It earns a high score for structure and efficiency.

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 tool with 5 parameters, no output schema, and no nested objects, the description covers purpose, usage, output format (coarse timestamps), and a verification workflow. It does not specify how start/end or max_results affect results, nor error handling, but the essential operational details are present. The absence of an output schema is mitigated by the mention of 'returns the project identity with its result' and 'coarse SOURCE timestamps'. Overall, it is sufficiently complete for an agent to call it correctly.

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 only 20% (only project_id has a description). The description compensates for query by stating it 'names one concrete visible event', and for project_id by emphasizing explicit scope. However, start, end, and max_results receive no semantic clarification in the description, and the schema only provides type and numeric bounds for max_results. Given the low coverage, the description partially addresses parameters but leaves significant gaps.

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 clearly states the tool performs 'focused semantic search across the COMPLETE indexed main-video filmstrip' and returns 'coarse SOURCE timestamps'. It distinguishes itself from transcript-based search and from sibling tools like look_at by explicitly contrasting with 'serial whole-video look_at probing'. The purpose is unambiguous and tied to a specific resource (the indexed filmstrip).

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?

It gives explicit when-to-use conditions: 'Use once for a long source when requested highlights are visual rather than transcript-searchable' with concrete examples (gameplay saves/fails, gestures, product appearances). It also provides an exclusion: 'Never replace it with serial whole-video look_at probing' and prescribes a follow-up verification step with 'ONE batched look_at call'. This fully guides an agent on when and how to use it vs. alternatives.

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