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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description's real contribution is the retention and pagination semantics: a capped newest-100 window plus has_more for older retained records. It also discloses the shape of the payload (persisted membership, targeted-response evidence, separate access_state) and one notable exclusion (invitation capabilities), which is context an agent can't derive from annotations.

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?

Two compact sentences, front-loaded with the return scope before the finer payload details, and no filler. It is dense with domain jargon but every clause carries information.

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?

With no output schema, the description takes on responsibility for describing the return payload and does so reasonably — retention window, has_more, included fields, and one exclusion. It could go one step further and explain how has_more is acted upon (pagination vs. archival), but it is otherwise sufficient for a single-parameter read 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?

With a single parameter, 100% schema coverage, and a constraint pattern documented in the schema, the description adds no meaning about room_id beyond what the schema already says. Baseline 3 applies because the schema does all the parameter work.

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 states a specific verb and resource — 'Returns the newest 100 invitations issued by the live room agent manager' — and implicitly contrasts with create_invite by being a listing rather than an issuing operation. It doesn't name or explicitly distinguish itself from any of the many siblings, so it stops short of a 5.

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?

There is no guidance about when to call this versus adjacent tools such as catch_up, room_situation, or create_invite, and no stated prerequisites beyond the room_id. The title 'Check your invitations' hints at the use case, but the description itself leaves routing to inference.

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