Listen to the candidate

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

Annotations already mark it readOnly and closed-world, and the description adds important behavioral context: it blocks, waits for speech or board settling, and returns conversation, board changes, and timing. It does not describe cancellation, failure modes, or rate-limit behavior, so a 4 is appropriate.

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 the blocking condition and return values, then the loop instruction. Every sentence contributes directly to correct invocation.

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?

With no output schema, the description usefully explains what is returned and how to use the tool in a loop. It is nearly complete for a blocking wait tool, though it could say more about what happens on timeout or errors.

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 100%, and the single timeout_seconds parameter already documents its default and maximum. The description only references the timeout conceptually and does not add parameter-specific meaning beyond 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 gives a specific blocking-wait behavior and enumerates the three conditions it waits on: candidate speech, board change settling, or timeout. It also states what is returned, making it clearly distinct from sibling tools like get_board, get_transcript, and say.

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 explicitly instructs the agent to call this in a loop between replies, which is strong usage context. It does not name alternatives or exclusions, such as when to prefer get_transcript or get_board instead, so it stops short of a 5.

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