Call status, transcript and summary

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

Annotations already cover the safety profile (readOnlyHint, openWorldHint), yet the description adds meaningful context: which providers produce the transcript/summary, that the price returned is the actual charge, and — most valuably — that transcript text is untrusted callee speech, a security-relevant note an agent should know before acting on returned content. It stops short of describing behavior for in-progress or missing calls.

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 sentence, front-loaded with the resource and the return payload, with parentheticals used for provider attribution rather than padding. No sentence is wasted.

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 and no annotations describing returns, the description does the work of enumerating return fields (status, duration, price, transcript, summary, opt-out detection). It omits error/edge behavior such as calls still in progress or unknown callIds, which is the only real gap.

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 0%, so the description must carry both parameters, but it only implicitly covers transcript retrieval via its mention of transcript/summary and says nothing about the includeTranscript toggle or the callId format. With two undocumented params, partial compensation lands at the baseline.

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?

Names a specific verb (Fetch) and resource (a placed call) and enumerates exactly what comes back: status, duration, actual price, transcript, and summary, including provider attribution. This is clearly distinguishable from siblings like place_call, list_calls, and end_call without opening any schema.

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 phrase "a placed call's" implies usage after place_call, and the required callId signals the retrieval pattern, but no alternative is named and no when-not condition is given (e.g., use list_calls to enumerate calls rather than fetching one by id). Usage is inferable but not stated.

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