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

The description clearly states 'Nothing is attached or created,' which is the key behavioral trait for a dry-run tool. Without annotations, it carries the burden well but doesn't mention error handling or whether argument validation occurs during preview.

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 sentences, front-loaded with what it shows, followed by the no-side-effect guarantee, then the required workflow. Every sentence is necessary and there is no redundant phrasing.

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 18 parameters and no output schema, the description covers the essential workflow and safety. However, it does not describe the return format of the preview (e.g., a textual summary or structured diff), which would help an agent interpret the result.

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 description coverage is only 33%, so the description must compensate. It highlights several parameters (connection_id, phone_number_id, call_objective, voice_id, accept_incoming) but leaves many of the 18 parameters (e.g., speed, emotion, ambient_sound) unexplained, so it only partially fills the gap.

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 explicitly states it shows what setup_phone_agent would do with the same arguments, listing specific aspects (channel, number, objective, voice, inbound). It directly names the sibling tool it precedes, making the purpose 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?

It gives explicit when-to-use guidance: 'ALWAYS call first and show the user, then call setup_phone_agent with the same arguments after approval.' This covers both the action and the required sequence.

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