send_dtmf

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

With no annotations, the description must disclose behavioral traits. It only lists parameters and a generic return type, omitting side effects, prerequisites (e.g., active call), error conditions, and whether the operation is idempotent or blocking. This is insufficient for a mutation-style tool.

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 a tightly structured docstring with Args and Returns sections. It front-loads the purpose and every line adds value. No unnecessary content.

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?

For a simple tool, it covers the necessary parameter info but lacks lifecycle context (e.g., must be used on an active call). The generic schema wrapper adds confusion, and the absence of an output schema means the return type 'Dict' is vague.

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 coverage is 0% with only a generic 'request' object. The description compensates by listing call_control_id, digits, and duration_millis with types and defaults. However, it doesn't clarify how these map to the schema's 'request' wrapper, creating structural ambiguity.

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 'Send DTMF tones on a call', which is a specific verb and resource. It distinguishes itself from sibling tools like playback_start, speak, and transfer, which are for other call media operations.

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 during an active call by referencing a 'call_control_id'. It doesn't explicitly mention alternatives or when not to use, but among the telephony siblings, this is the only DTMF tool, so the context is clear.

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