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

Annotations already cover the safety profile (readOnlyHint, idempotent, non-destructive), so the description's job is to add context. It does: ordering, what is and isn't included in the payload, and the important empty-state caveat 'returns nothing until the account has placed a call'. It stops short of describing result volume limits or how many calls 'recent' spans.

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?

Three tight sentences: what it returns first, why you'd call it second, routing to alternatives third, plus a one-line edge case. No repetition of 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?

No output schema exists, and the description compensates by enumerating the returned fields and the transcript exclusion. The empty-result condition is disclosed. Minor gap: no mention of result cap/pagination behavior beyond the limit parameter, though the schema covers limit itself.

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% — both limit (1-50, default 10) and account_key (OAuth vs API key) are documented in the schema. The description adds no parameter guidance of its own, so the baseline of 3 applies.

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 specific verb and resource ('recent calls on the user's account'), plus ordering ('newest first') and the fields returned ('status, answers and outcome'), with an explicit exclusion ('no transcripts'). It is clearly distinguishable from get_call and get_batch, which it names.

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 concrete discriminating use cases — 'to find a call_id' and 'what did they quote last time?' — and names the alternatives (get_call for live status/transcript, get_batch for a batch) with the conditions that select them. 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.