get_call_transcript

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

With no annotations, the description carries the full burden. It discloses behavior beyond the basic 'get' action: transcripts are chronological with timestamps, and not all calls have transcripts (missed/short/no-STT) returning 'No transcript available.' This adds useful behavioral context that is not apparent 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 description is front-loaded with the main purpose in one sentence, followed by return-format detail and a well-structured 'How to get the activity name' section using bullets. It is not overly verbose and each section adds value, though the parameter guidance is somewhat lengthy.

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?

The tool is simple (one parameter) with an output schema but no annotations. The description covers the return value (timestamps, 'No transcript available'), the parameter source, and an example. It does not discuss error handling or auth, but given the low complexity and rich parameter description, it is sufficiently complete for an agent to invoke correctly.

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?

The schema only defines 'activity' as a string, with 0% semantic coverage. The description compensates excellently: it explains the parameter is the activity name/ID, provides an example ('activity_699351d84288a407003861'), and explicitly tells the user where to find it (the 'Activity' field in list_calls/get_call or the 'name' field from list_activities). This is far beyond the schema.

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?

The description opens with 'Get the full speech-to-text transcript of a specific call,' which is a specific verb+resource combination. It clearly differentiates from siblings like list_call_transcripts by focusing on a single call's transcript rather than a list.

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 description implies when to use this tool (when you need a specific call's transcript) but does not explicitly state alternatives/exclusions. It does not mention 'use list_call_transcripts to list all transcripts' or 'use get_call for call metadata.' The note about calls without transcripts gives some context, but no direct comparison to sibling tools.

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