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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds useful behavioral context: it returns a recent conversation snapshot plus presence details (appearance, activity, position, live conversations). This goes beyond the annotations, clarifying the read-only nature and the richness of the response. It doesn't specify pagination or time windows, but that's minor given the annotations cover safety.

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, concise sentence that front-loads the main purpose (recent conversation) and then lists the additional data. It's efficient with no wasted words. It could structure the presence details as a list, but it's readable and to the point.

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 the complexity of the tool (room state with multiple aspects) and no output schema, the description provides a good overview. It covers the presence information and conversation history, which is most of what an agent needs. It might not mention that the 'room' parameter can be an instance, but that's in the schema. It's complete enough for a read-only 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?

Schema description coverage is 100%, so both 'room' and 'limit' are fully described in the schema. The description adds a little by implying the room context (recent conversation + presence) but doesn't explain the 'limit' parameter's impact on presence data. Since the schema carries the semantics, a baseline 3 is appropriate.

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 what the tool does: it reads recent conversation in a room and provides presence information (who is present, their appearance, what they are doing, and live conversations). This is specific to a room resource and distinct from read_conversation, which likely targets a single conversation thread. However, it doesn't explicitly contrast with read_conversation or enter_room.

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 implies usage for getting room state and recent messages, but it doesn't explicitly state when to use this versus read_conversation or enter_room. There's no when-not guidance or alternatives mentioned. The schema hints that 'room' can be an instance key from enter_room, which provides some context but not explicit selection criteria.

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