Phone Ask

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

With no annotations, the description carries the behavioral burden well: it discloses that the answer arrives as kind 'answer', that wait=N blocks for up to N seconds, and that calls can be refused for grants or private terms. It does not explain timeout behavior or whether questions are spoken aloud, but the core refusal and blocking semantics are unusually clear.

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 compact and front-loads the tool's purpose before moving into wait behavior and refusal rules. The parenthetical about grants is dense but carries necessary operational guidance, and no sentence is purely redundant.

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 four-parameter phone interaction tool with an output schema, the description covers purpose, answer delivery, blocking behavior, and the main refusal/override cases. The only notable gap is sender semantics, which is minor relative to the behavioral context provided.

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%, so the description must compensate for all four parameters. It meaningfully explains wait and override_grant, and its 'yes/no question' framing gives context for text, but sender is not described at all. That leaves one of four parameters undocumented despite otherwise helpful parameter-level detail.

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 a specific action: asking a yes/no question over the phone and receiving an answer as kind 'answer'. It is more specific than the name alone, but it does not explicitly distinguish itself from nearby phone tools such as phone_say, phone_offer, or phone_buttons.

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?

It gives clear usage context and important exclusions: it is refused when a standing grant already answers the question, and the agent should act on the grant and caption the action instead. It also explains override_grant as the escape hatch when the grant does not fit, though it does not explicitly compare against other phone interaction tools.

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