get_call_transcript

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the dependency on CallScribe, the non-retroactive transcription policy, the 404 behavior under two different conditions, the error envelope hint, and the exact return structure (JSON with segments, confidence scores, durations). This is exceptionally transparent and helps the agent handle failures gracefully.

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 well-structured with clear sections (Args, Returns, warning). Every sentence contributes essential information—prerequisites, error semantics, parameter hints, return format—with no filler. The warning is appropriately highlighted with a date and a clear explanation of the 404 meaning. It is long but earns its length.

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?

Given a 2-parameter tool with a complex operational context (feature flags, API changes, ambiguous error codes), the description covers all necessary aspects: when to use, what to expect, error interpretation, and return structure. It even notes the output schema details (segments, confidence, durations) despite having an output schema, making it self-contained. Nothing an agent needs to call and interpret this tool 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?

The schema provides zero description coverage, so the description must explain the parameters. It does: call_id is given a format hint ('CAL...' id) and account_id is described as auto-resolving if omitted. This adds real semantic value beyond the bare type definitions and prevents misuse.

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 a specific verb and resource ('Get the AI transcript for a call'), immediately distinguishing it from related sibling tools like get_call_recording or call_summary. The purpose is unambiguous and leaves no question about what the tool returns.

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 explicitly states the prerequisites (CallScribe enabled at the time of call, Premium Conversation Intelligence as of a specific date) and explains the critical 404 ambiguity, telling the agent when the tool will not work. This goes beyond vague guidance and gives clear operational constraints.

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