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

Adds substantial behavior beyond annotations: pre-join history is not shared, the room is notified of the join, 403 conditions, idempotency for existing members, and the required request signing. This complements the annotation hints (idempotentHint, destructiveHint=false) rather than merely repeating them.

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 core action and effect, then layers failure modes and auth in a single dense paragraph. Every sentence carries information, though the run-on structure could be broken up for scannability.

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 explaining resulting state, notification side effects, history boundaries, error conditions, and auth requirements. Nothing an agent needs to invoke this correctly is missing.

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 100%, so both parameters are already documented; the description's restatement of conversation_id's format (owner-room:<uid>:<id>) largely duplicates the schema. Baseline 3 is appropriate since the schema carries the parameter meaning.

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 (accept) and resource (room invite) and immediately defines the resulting state: 'you become a member of that person's room.' An agent can distinguish it from decline_room_invite and leave_room 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?

Clearly states the precondition (an invite to agent_id must be waiting) and the failure mode (403 if withdrawn, declined or never sent), plus what to do after joining via send_message. It does not explicitly name the sibling alternatives (decline_room_invite, leave_room), but the context is unambiguous.

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