Search transcriptions

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

Beyond the readOnly/openWorld annotations, it discloses the search corpus (newest 500 recordings), exclusions (processing or failed ones skipped), the truncation signal ('truncated is true when there may be older ones, which are not read'), and the per-result cap of five matches with start offsets. These are non-obvious behavioral limits an agent cannot infer from the schema.

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 scope statement is front-loaded and every clause carries information, but the single long sentence with stacked parentheticals reads as a run-on and takes effort to parse on first pass.

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 provided, the description still conveys the return shape (up to five matches per result, second offsets, truncated flag) plus the next step, so an agent knows both what it will get back and how to drill in. Nothing essential for correct invocation is missing.

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 coverage is 100%, so the baseline is 3; the description earns more by clarifying that the query is matched as one contiguous phrase in transcript text and should be a distinctive word or short phrase rather than a natural-language question. It conveys matching semantics the schema's 'The word or phrase.' does not.

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?

Opens with a concrete question the tool answers ('which recordings said something, and when') and specifies the matching surface: the words as one phrase in what was said, not in titles. That explicitly separates it from title/metadata-oriented siblings like list_transcriptions.

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?

Tells the agent how to phrase the input ('give a distinctive word or short phrase, not a question') and routes follow-up work to get_transcript's from/to instead of reading whole transcripts. It never explicitly states when NOT to use it (e.g., you already know the recording), so it falls short of the top band.

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