Search inside a video

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: results are per-occurrence, and each hit is a timestamped deep link that jumps to that second — important since no output schema exists.

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?

Two sentences, zero filler, with the primary capability front-loaded and the sibling contrast second. Every clause earns its place.

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 correctly takes on the burden of describing the return value (timestamps as jump links). It leaves the language parameter undocumented in both description and schema, a minor gap for an otherwise self-contained 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 75%, with query, video and context_segments documented in the schema and only language undocumented. The description adds no parameter-level meaning (no syntax, no default behavior, no language semantics), so the baseline 3 applies.

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?

States a specific verb+resource ('Find every place a phrase is said in a video') and specifies the return shape (timestamps as jump links). It explicitly distinguishes itself from the sibling get_transcript by framing the alternative ('pulling a whole transcript').

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?

'Use this instead of pulling a whole transcript when you only need to locate something' gives a clear selection condition and points at the alternative behavior. It stops short of naming the sibling tool get_transcript explicitly or stating exclusions, so it is clear context rather than fully prescriptive routing.

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