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

Annotations only provide a title, so the description carries the full burden. It states 'Read' implying a non-mutating operation, but fails to disclose return format, pagination, whether messages are marked as read, or behavior with invalid room IDs. The term 'recent' is vague without limits.

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 a single, direct sentence starting with the action verb. Every word is informative, with no filler or redundant structure.

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?

The tool has one parameter, no output schema, and minimal annotations. The description explains the action and target but leaves key details unspecified, such as what a 'recent conversation' contains or how the response is structured. For a simple read tool, this is adequate but not robust.

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 input schema already provides a complete description for the 'room' parameter ('Room id, as returned by Rooms'), covering 100% of parameters. The tool description adds no additional information about parameter usage or syntax, so it meets the baseline for high schema coverage.

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 the verb 'Read' with a specific resource ('recent conversation in a discussion room'), making the tool's function clear. However, it doesn't explicitly differentiate from sibling tools like chat or chat_rooms, relying on the verb to imply read-only vs. sending/listing.

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 provides no guidance on when to use this tool versus alternatives like chat or chat_rooms. It offers no context about prerequisites, such as needing a room ID from chat_rooms first, nor any exclusions.

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