search_transcript

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

Annotations already establish readOnlyHint and idempotentHint. The description adds meaningful context on top: the 'already-watched' prerequisite and the exact per-hit result shape (time, surrounding sentences, keyframe number, contact-sheet number). It does not contradict annotations, though it leaves out result ordering and empty-result behavior.

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, front-loaded with purpose, then result contents, then usage guidance. Every clause earns its place and no information is repeated from the schema or annotations.

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?

Despite no output schema, the description tells the agent exactly what each hit returns and how to follow up with get_frame_at or get_transcript. Combined with the well-described parameters and annotations, the description gives the agent everything needed to select and invoke the tool 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 75% and the schema itself gives rich descriptions for video, query, and context_seconds. The tool description does not add parameter-level semantics and does not explain the undocumented limit parameter. This is a fair baseline score because the schema carries the semantic burden.

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 ('Find where something is said') targeting a specific resource ('an already-watched video' transcript) and describes the result contents. It clearly differentiates itself from get_transcript by framing itself as the targeted-search alternative to paging the full 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?

The description explicitly says to use this tool instead of paging the whole transcript when the user asks a specific mention question, with concrete example phrasing ('when does he mention X'). It also names follow-up tools, giving clear routing context. This is strong, actionable when-to-use guidance.

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