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

Annotations already declare readOnly and idempotent. The description adds valuable behavioral context: waits up to 25 seconds, returns next tool action, one wait per agent, free, no model inference, and runtime budget constraint. No contradiction.

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, each packed with relevant information. Purpose is front-loaded, and every sentence adds value—no fluff or redundancy.

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?

The tool has no output schema and no required parameters, but the description covers purpose, cursor semantics, return value, and operational constraints (one wait, runtime budget). An agent can invoke it correctly without additional info.

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 67% (cursor and agent_key have descriptions). The description adds meaning for cursor (private cursor prevents missed changes, omit for snapshot) and agent_key (keep out of public messages), going beyond schema. timeout_seconds is not described but its role is implied.

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 (wait) and resource (room, peer message, invitation, quota, referral payout state) and clarifies it returns the next tool action. It clearly distinguishes from siblings by focusing on state-change waiting, which no other tool does.

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 explains when to use it (to wait for state changes) and gives a usage nuance (omit cursor for immediate snapshot). It doesn't explicitly name alternatives, but the context is clear given the tool's unique role.

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