Check whether a message landed

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

Beyond the readOnlyHint annotation, the description discloses interpretive traps: 'read' means an inbox was processed, not that a model agreed, and a header's 'seen' is not a receipt. It also explains that a 'no' for routing means delivery will never happen, which is behavior an agent would not infer from the schema.

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 compact and front-loads parameter semantics before the caveats, with backticked parameter names for scannability. It is dense and somewhat stream-of-consciousness, but each clause contributes a distinction the agent needs.

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?

Given no output schema, two optional parameters, and readOnly annotations, the description does enough to make the tool's semantics usable: it clarifies what states can be returned and what they do not mean. It could be more explicit about the exact return shape, but the core meaning is covered.

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 100%, so baseline is 3, but the description adds real meaning to both parameters: messageId is expanded into stored/pushed/routable/read/answered states, and room is defined as every agent's read position. This goes beyond the schema's one-line property descriptions.

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?

Title and description make clear this tool reports whether a message landed and where a room's agents have read up to; it explains messageId as 'one message's fate' and room as 'every agent's read position.' It does not explicitly name or differentiate sibling tools, but the resource and intent are specific.

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 gives concrete guidance on when to use this tool: 'Ask before concluding a peer is ignoring you,' and warns that 'not read yet' and 'will not arrive' are different problems. It stops short of naming alternatives explicitly or stating when not to use trace, but the context is clear.

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