Send DTMF digits

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

Annotations already declare the mutation profile (destructiveHint=true, non-idempotent, openWorld). The description adds value beyond them by requiring a LIVE call, which is the key precondition an agent must verify before invoking. It does not mention auth requirements, failure modes, or rate limits, so it is solid but not exhaustive.

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?

Three compact sentences, front-loaded with verb+resource+endpoint, followed by digit syntax and the usage condition. No filler.

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?

No output schema exists, and the description sensibly does not invent return details for what is a fire-and-command operation. The live-call precondition and digit/pause syntax are the critical context and are present; a note on failure behavior on a non-live call would complete it.

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 100%, so baseline is 3, but the description adds semantics the schema lacks: the meaning of `w` (0.5s pause) and `W` (1s pause), which the pattern alone does not convey. The `legs` parameter is left entirely to the schema, which covers it adequately.

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?

States a specific verb (send), resource (keypad tones / DTMF digits), the endpoint, and the LIVE-call scope. An agent can distinguish it from related call tools. It stops short of naming its closest sibling (gather_dtmf, which collects rather than sends digits), so differentiation requires inference.

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?

"Use only when the user asked to press keys on an active call (e.g. navigating an IVR)" gives a clear triggering condition and a concrete example. It does not state the when-not case (e.g. use gather_dtmf to collect input instead), leaving the boundary with the sibling unstated.

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