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

Annotations already cover read-only/idempotent/non-destructive, yet the description adds substantial non-obvious behavior: reads do not consume the shared-message quota, join requests require user review and are never auto-approved, and it is a bounded long-poll rather than true real-time delivery. This is rich context beyond the structured data.

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?

Dense but front-loaded with the core purpose, and each sentence carries operational value (cadence, quota, cursor, review policy). Slightly packed with several ideas in one paragraph, but there is little waste.

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?

No output schema exists, yet the description conveys the return shape (array of events), the cursor field to persist, and empty-result behavior. Combined with the usage and quota guidance, an agent has everything needed to call and consume it correctly.

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%, with `connection` well-documented in the schema. The description compensates for the undocumented `after` parameter by explaining cursor semantics: persist the last seq after recording pending work, pass it as `after`, and retain the cursor on an empty result. It adds real meaning over the bare integer 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?

States a specific verb (check/wait) and resources (new accessible messages, creator-only join and security events) with a concrete scope limit (25 seconds). This clearly differentiates it from pull-based siblings like messages_search or tincan_open.

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 explicit when-to-use (authorized ongoing listening in a host that cannot maintain a stream), a recommended cadence (scheduler every 5 minutes by default), and an explicit when-not (do not loop in the foreground or claim real-time delivery). Nothing is left to inference.

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