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

With no annotations, the description carries the full burden. It discloses persistence across a session, key-based sharing, size limits, and a 48-hour TTL that clears the room. It also clarifies that it is the only place the server keeps anything and only stores deliberate inputs. This is comprehensive behavioral disclosure.

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 tightly written, starting with the core purpose, then the operations, then constraints and lifecycle. Every sentence adds value, and the most critical information (what it is) is front-loaded. No redundancy or filler.

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 simple tool with three parameters and no output schema, the description covers the essentials: operations, size limits, TTL, and the intentional scope. It doesn't explicitly state return values (e.g., what list returns), but given the simplicity and the absence of an output schema, this is a minor gap. The description is adequate for correct invocation.

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?

Although the schema has 0% description coverage, the description adds meaning by explaining the operations (put, get, list, delete, empty) and implying how name and value are used. It compensates well for the missing schema descriptions, though it doesn't explicitly map each parameter's role in every operation (e.g., that get/delete require name).

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 clearly states the tool's purpose as shared state between agents, listing the exact operations (put, get, list, delete, empty). It distinguishes itself from the sibling room_key by requiring a key and describing the key-sharing behavior, making it easy for an agent to know this is the state store while room_key likely manages keys.

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 context on when to use this tool: as coordination space for work in progress, not an archive, and notes size limits (4kb/item, 32kb/room) implying it's not for large data. However, it does not explicitly name alternative tools for other use cases (e.g., for archival or larger storage), so an agent must infer the boundaries from the constraints.

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