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

Annotations already cover the read-only/idempotent safety profile, but the description adds domain-specific behavior beyond them: what a null cluster with speaker 'No speaker label' means, the instruction not to attribute those words to a neighbour, and the availability limitation for document-granularity transcripts. This is exactly the kind of caveat structured fields cannot express.

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?

Front-loaded with the core behavior in the first sentence, followed by a caveat paragraph and an availability paragraph. Every sentence carries information, though the multi-paragraph layout is slightly heavier than strictly needed for a three-parameter tool.

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 an output schema present, return-value detail is unnecessary; the description instead covers the gaps an agent needs — special-case turn semantics and the transcript-type limitation that would otherwise cause a wrong call.

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, but the description adds real semantics: the window is defined by overlap with the interval rather than containment, which changes what turns come back. It does not restate the 5-minute cap, but the schema already carries that.

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 precise verb and resource — 'Return speaker turns overlapping [start_ms, end_ms] with their text' — plus the intent ('for checking context'). It also differentiates itself from the citation/document route for transcripts without timing, so an agent can tell when this tool is the right one.

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?

Gives an explicit when ('for checking context' around a moment) and an explicit when-not ('Not available for official transcripts without timing (timing_granularity "document")'), naming the alternatives: the result's document_url or resolve_citation for surrounding turns. Nothing is left to inference.

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