send_dtmf

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

With no annotations provided, the description carries the full burden. It discloses the action ('Send DTMF tones') which implies a write/mutation operation, and specifies parameter details like digit format and default duration. However, it lacks critical behavioral context such as whether this requires specific call permissions, if it's synchronous/asynchronous, error conditions, or rate limits. The description adds some value but doesn't fully compensate for the absence of annotations.

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 perfectly structured and concise: a clear purpose statement followed by well-organized parameter documentation in a bullet-like format. Every sentence earns its place by providing essential information without redundancy. The information is front-loaded with the core purpose immediately stated.

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 the tool's moderate complexity (sending DTMF tones during calls), no annotations, and no output schema, the description does reasonably well by explaining parameters thoroughly. However, it lacks important contextual information about the operation's behavior (e.g., synchronous nature, error handling), the structure of the return value beyond 'Dict[str, Any]', and integration with call states. For a mutation tool with zero annotation coverage, more behavioral context would be beneficial.

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 description coverage is 0% (only a generic 'request' object), but the description provides comprehensive parameter details: it names three parameters, specifies required/optional status, describes valid digit formats ('0-9, *, #, w, W'), and indicates default values. This significantly compensates for the poor schema coverage, though it doesn't fully explain the nested 'request' object structure mentioned in 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 clearly states the specific action ('Send DTMF tones') and resource ('on a call'), with a precise verb+resource combination. It distinguishes itself from sibling tools like 'playback_start', 'speak', or 'hangup' by focusing specifically on DTMF tone transmission rather than audio playback, voice synthesis, or call termination.

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 usage context through the parameter descriptions (e.g., 'call_control_id', 'digits'), suggesting it should be used during an active call to send DTMF tones. However, it doesn't explicitly state when to use this tool versus alternatives like 'playback_start' for audio or 'speak' for text-to-speech, nor does it mention prerequisites like requiring an active call or specific call states.

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