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

Annotations already declare readOnly/idempotent/closed-world, so the bar is low, yet the description adds real behavioral context: transcripts arrive as windows that must be resumed, and the recording is deliberately not returned here but plays in-app. That last point prevents an agent from hunting for audio data that will never appear.

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?

A single dense paragraph, front-loaded with the returned contents, then paging behavior, then the recording caveat. Despite the long enumerations, each clause carries information an agent needs and nothing is repeated.

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?

There is no output schema, so the description bears the full burden of describing the response, and it does so field-group by field-group while also covering pagination and the audio exclusion. Nothing material 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 baseline would be 3; the description goes beyond it by explaining that transcript_from continues the previous window and that transcript: false suppresses the payload entirely, and it clarifies speaker framing ('we are Dan to the merchant') which the schema does not mention.

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 specific verb+resource ('One call in full') and enumerates the actual payload: lead, caller identity, timing, outcome, analysis, objections, notes, transcript. An agent can distinguish this from the search_* siblings by the singular scope, though no sibling is named explicitly for the 'find it first' step.

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?

Guidance is limited to in-tool options — pass transcript_from to read further, or transcript: false to skip — rather than when to choose get_call over search_calls or get_lead_timeline. Usage is implied by the 'one call in full' framing but never stated as a rule.

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