debug_call

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It thoroughly enumerates the returned data: call status, failure reasons, errors, transcript, analytics, latency, cost, config, event timeline, and detailed LLM insights (usage, turns, toolCalls). It also clarifies it works for any call state. This gives an agent a complete picture of what the tool does and returns, with no hidden side effects.

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 long but front-loaded with the purpose, then systematically details return fields and capabilities. Every sentence adds useful information, and the structure is logical (purpose, general returns, LLM specifics, state support, usage). It is appropriately sized for the tool's complexity, though it could be slightly tightened without losing value.

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 must explain return values, which it does exhaustively—covering all major categories plus granular LLM insights. It also explains the input format and the fact that it works across all call states. Nothing an agent needs to correctly 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 already describes the single parameter call_id with an example, so coverage is 100%. The description reinforces the format by repeating the example and explicitly stating 'Use a callId (e.g. CALL-1234567890-abc123)', which adds value beyond the schema. This slightly exceeds the baseline of 3 for full coverage.

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 clearly states the tool's purpose: 'Get detailed info about a single call' with specific use cases (check call status, debug failures, get transcripts). It distinguishes itself from list_calls by explicitly targeting a single call, and the verb+resource (get/debug a call) is unambiguous.

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 provides clear context for when to use the tool (check status, debug, get transcripts) and notes it works for calls in any state. It implies it's for a single call (vs. list_calls for multiple) but does not explicitly name an alternative or state when not to use it. This is clear guidance but lacks explicit exclusion of siblings.

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