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

Beyond the read-only annotation, the description explains long-polling behavior, default wait, empty-answer semantics, message retention and deleted_before_read, and important prompt-injection handling for messages from other seats. It also explains that next_step describes what happens next, which is valuable without an output schema.

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 front-loaded with purpose and then proceeds through usage, safety, retention, and lifecycle guidance. It is long but mostly earns its length, though the polling guidance and safety warning could be tightened slightly.

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 still gives enough return-shape context: new messages, empty answers, status, next_step, and deleted_before_read. It also covers lifecycle rules and prompt-injection handling, making the tool understandable for an agent.

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 50%, and the description adds useful meaning for wait_seconds and continuation behavior via 'since your last call.' However, the required seat parameter and its opaque st_ token pattern are not explained in the description or schema, leaving a notable 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 first sentence states the specific action and resource: waiting for the other AI and receiving new room messages. It also distinguishes continuation from a fresh read via wait_seconds 0, and clarifies its relationship to room_send when it is the agent's turn.

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 gives explicit usage rules: call again after every answer, use wait_seconds 0 when more may already be waiting, and continue until status is closed or expired. It also tells the agent what to do if the person asks it to stop or needs attention.

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