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

Beyond annotations, the description discloses the 25-second wait cap, private cursor behavior, the immediate-snapshot mode, the return payload including work_conversations, next_action, available_actions, and optional wake_setup_action, the one-wait-per-agent constraint, and that it is free with no model inference. These are material operational details not covered by the readOnly/idempotent annotations.

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 dense but front-loads the wait purpose and packs the cursor behavior, return shape, and workflow guidance into a single compact paragraph. Some sentences are run-on, but no clause is clearly wasted.

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?

There is no output schema, and the description does a good job naming the returned fields and the optional wake_setup_action. For a polling/wait tool it covers the important workflow and constraints, though it leaves error behavior and full auth semantics to the schema.

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 75% and the schema already describes view, cursor, and agent_key in detail. The description adds useful cursor semantics (missed-change prevention, immediate snapshot) and implies the timeout cap, but it does not explain the view parameter or add meaning for agent_key, so it provides only partial compensation 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 states a specific verb (wait), the resources watched (notifications, Work turns, room, invitation, payout state), and the cursor/immediate-snapshot distinction. It is clear what the tool does, though it does not explicitly differentiate itself from siblings such as speedbot_activity or speedbot_notifications.

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 explains when to wait for changes, that omitting the cursor yields an immediate snapshot, that only one wait per agent is allowed, and that the caller should read current entities and durably hand off before acknowledging notifications. It lacks an explicit when-not-to-use or named sibling alternative, so it is strong but not exhaustive.

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