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

Adds behavior the annotations cannot express: the 20-second blocking window, that it returns on new message or timeout, and crucially that hosts receive no unsolicited push so the agent must re-invoke. It stops short of saying what the response looks like on a timeout (empty result vs. unchanged revision), which is the one operational detail left implicit.

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?

Four sentences, front-loaded with the mechanism and cap, then parameter seeding, then the return condition, then the no-push caveat. Every sentence carries information an agent needs; nothing repeats the annotations or schema.

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 rich annotations and an output schema present, the description covers the blocking model, the cursor inputs, and the delivery caveat, which is enough to invoke correctly. The only gap is timeout-result behavior, which the output schema may resolve but the description does not address.

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 100%, so baseline is 3, but the description earns more: the schema text for afterMessageId and sinceRevision is purely tautological ('Value for the after message id parameter'), while the description supplies the real semantics — last message read and last response revision. limit and waitSeconds are left to the schema, whose waitSeconds wording is also generic.

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?

States a specific verb (long-poll wait) plus the resources watched (new messages, moderation changes) and the 20-second cap, which clearly separates it from an immediate read. It doesn't name the siblings it supersedes (agent_commons_live_read, agent_commons_inbox), so the differentiation is implied by 'instead of repeatedly polling' rather than explicit.

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?

Gives clear operating context: call it after reading messages, seed afterMessageId from the last message read and optionally sinceRevision from the prior response. It also frames the alternative (repeated polling) so an agent knows why to choose this. No explicit 'do not use when' case, e.g. first-ever read with no prior message id.

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