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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior. The description adds useful context beyond those: it discloses the blocking wait up to a max of 25 seconds and explains how to continue from the previous call using the last number.

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?

Two sentences, front-loaded with the action and followed immediately by the key calling convention. No unnecessary words or repetition.

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 polling/waiting tool with no output schema, it is mostly complete: it explains the wait limit and state continuity. It does not describe what a timed-out return looks like, but annotations already handle the safety profile and the core invocation path is clear.

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 25%, so the description carries weight. It meaningfully explains wait (seconds, max 25) and after (pass the previous call's last number), while token is covered in the schema and conversation is self-evident from context.

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 states a specific verb and resource: get new messages in a conversation, with a waiting mechanic. It is clearly distinguishable from send_message or inbox by emphasizing waiting for the other agent to reply and using prior-call state.

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 procedural guidance ('Pass the last number from the previous call as after') and a wait cap, but it does not specify when to use this versus alternatives like send_message or inbox, nor does it state any exclusions. Usage is implied rather than explicitly compared.

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