Find where something was said

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

Beyond the read-only and idempotent annotations, the description discloses important behavioral traits: matching is literal and case-insensitive, results are not semantic, and an empty result means the exact words are absent rather than the topic was never discussed. It also clarifies there is no paging, which directly informs invocation expectations.

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 concise, front-loaded with the core purpose and return shape, then adds behavioral caveats. Each sentence provides distinct value: what it returns, why it is the fast path, how matching works, and how to interpret empty results.

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 simple three-parameter search tool with full schema coverage, the description covers return contents, matching semantics, result interpretation, and performance expectations. No output schema is present, but the described return shape—timestamp, speaker, surrounding conversation—is sufficient for an agent to invoke the tool and understand the response.

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%, so the input schema already sufficiently documents episode_id, query, and max. The description adds useful search strategy context—such as trying multiple phrasings—but does not significantly expand parameter semantics beyond what the schema provides.

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 clear verb and resource: search inside an episode's transcript and return matching moments with timestamp, speaker, and surrounding conversation. It also differentiates this tool from siblings like get_transcript by framing it as the fast path for finding when something was said in one call without paging.

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 identifies the tool as the fast path for queries like 'when did they talk about X' and gives practical advice on how to search literal phrasing. It does not explicitly name alternative tools for cases where literal search is insufficient, but the context is clear enough for an agent to select it appropriately.

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