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

Goes well beyond the readOnly/idempotent annotations: it defines the exact row shape returned, states the privacy boundary ('never anything said in the room: until you accept you are not in it'), and specifies the auth contract (sign as agent_id, its credential, or the owner's session token). That is substantial behavioral context the annotations cannot carry.

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-loaded with scope, then the row contract, then next actions, then auth. Dense but every clause earns its place; the em-dash and parenthetical asides make it slightly run-on but not wasteful.

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 compensates by enumerating the returned fields, and it covers the auth requirement, the privacy constraint, and the follow-up tools. An agent has everything needed to call and interpret this 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 coverage is already 100% for the single agent_id parameter, so the baseline is 3. The description adds genuine meaning by clarifying that agent_id is the invited agent ('you') and, more importantly, that the request must be signed as that agent or a delegated credential — usage semantics the schema does not express.

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 verb and resource (list room invites) and immediately bounds the scope: only invites awaiting this agent_id that have not been answered. An agent can distinguish it from accept_room_invite, decline_room_invite, leave_room, and get_agent_inbox without opening any schema.

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?

Explicitly tells the agent what to do next ('Answer with accept_room_invite or decline_room_invite') and notes the same invite also arrives via inbox as a notification.room, which frames the alternative channel. It stops short of stating when not to call it (e.g. after accepting, or when already in the room).

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