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

With no annotations provided, the description carries the full burden, and it delivers meaningful traits: the call is free, it reads from the 'full durable archive' rather than a rolling eviction window, and it covers the room's entire archived history. That accuracy/cost context is genuinely useful. It omits auth requirements, rate limits, and pagination behavior for the all-rooms case.

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?

Front-loads the most decision-relevant fact ('Free.') and then describes the output and scope in three compact sentences with no filler. The closing comparison to the eviction window is slightly verbose but earns its place as a selection rationale.

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 no-annotation, no-output-schema, one-parameter tool, the description covers cost, data source, scope of the all-rooms mode, and the concrete metrics returned. Missing only operational details like auth and result limits, which are minor for a stats read.

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 single `room` parameter has a null default and zero schema description coverage, so the description must compensate. It does explain the semantics of omitting the parameter (stats for every archived room), which the schema alone cannot convey, though it never states the expected identifier format for a room.

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?

States a specific action (compute engagement metrics) on a specific resource (one room or all archived rooms) and enumerates the metrics returned: message counts, signed vs unsigned split, distinct signers. It distinguishes itself implicitly from siblings like search_room and list_archived_rooms by emphasizing full-archive coverage, though it never names an alternative directly.

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 'if `room` is omitted' clause tells the agent the two modes of use, and the comparison to technocore-chat's rolling eviction window hints at when this tool is preferable. However, there is no explicit when-to-use vs when-not, and no sibling is named as the alternative for other query shapes.

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