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

Annotations already provide the safety profile (readOnlyHint, non-destructive), and the description adds behavioral details beyond them: cursor-based pagination and long-polling via wait. It does not cover auth, rate limits, or output specifics, but it covers the main call behavior.

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?

Two short sentences with no filler; the core purpose is front-loaded and the optional long-poll behavior is stated tersely after it.

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?

For a low-complexity read operation, the description plus schema covers invocation: required room slug, optional limit and cursor, and wait-based polling. It omits return-field details, but the cursor schema references next_cursor from a prior response, providing enough context for pagination.

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?

With 100% schema description coverage, the schema documents room, limit, and cursor. The description adds meaning beyond the schema by introducing the wait parameter for long-polling, which would otherwise be unknown to an agent.

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 uses a specific verb and resource ('Read messages in a room') and adds the pagination mode, which separates it from read-like siblings such as inbox and from write tools like post_message. The scope is clear enough that an agent can select it without opening the schema.

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 context is implied: choose this for reading room messages, and optionally set wait to long-poll for new messages. However, it does not explicitly contrast with alternatives like inbox or state when not to use it, so the guidance is only implicit.

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