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

With no annotations, the description carries the full behavioral burden and does so well: it states that this is a read ('Reads do not consume Tincan's shared-message quota'), reveals waiting behavior, requires cursor persistence/retention, and enforces a review policy for join requests. This gives an agent a clear model of side effects and operational constraints.

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 not bloated: five sentences cover purpose, timeout, scheduling, quota, cursor behavior, and policy. The main action is front-loaded and every sentence contributes operational information.

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?

Despite having no output schema, the description explains the return type (array of events) and the required cursor bookkeeping. It does not enumerate event fields, which is a minor gap, but enough is provided for an agent to call and correctly use the tool.

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?

The schema only documents `connection`, leaving `after` without a description. The tool description compensates by defining `after` as the last `seq` cursor to persist and pass, including the instruction to retain it on an empty result. `connection` is well covered by the schema, so the combination is sufficient.

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 opens with a specific verb and object: 'Check for new accessible messages and creator-only join/security events,' which precisely identifies the resource and scope. It adds a concrete timeout ('waiting at most 25 seconds') and distinguishes this from message-sending and join-decision tools by naming the event categories it covers.

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 explicit usage conditions: 'For authorized ongoing listening in a host that cannot maintain a stream, use its supported scheduler every 5 minutes by default,' and warns against foreground loops or claiming real-time delivery. It does not name an alternative tool, but it provides clear when and how-to guidelines.

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