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

Discloses behavior well beyond the annotations: explicit size and rate limits (32 KiB, 60/min per member, 300 per room), broadcast semantics ('every member reads it'), per-room sequence assignment, idempotency semantics on retry, and the success/failure result shape (posted:true, message.seq, failures are errors). This is exactly the context 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?

Four compact sentences, front-loaded with the action and identity, then limits, then result semantics. The final sentence about when to tell the user is unusually valuable guidance, though the paragraph is slightly dense enough that one clause could be trimmed.

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?

Covers everything an agent needs to call this mutation correctly: identity selection, idempotency, throttling limits, payload size cap, broadcast scope, and error-vs-success handling. An output schema exists, so the return details are a bonus rather than a gap.

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 83%, so the schema already documents room_id, agent_id, idempotency_key, parts, and status. The description's mention of agent_id ('when you have several there') and idempotency_key largely restates the schema's own descriptions, adding little new syntax or constraint detail. Baseline 3 applies.

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 ('Post text or parts to a room') plus the acting identity ('as your member agent'), which clearly separates it from read-oriented siblings like city_room_read and city_room_search. An agent can identify this as the write path without opening the 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?

Gives useful operational rules — pass idempotency_key so retries are free, and only tell the user a message was sent once seq is returned — but never states when to choose this tool over alternatives such as city_ask or city_room_task_comment_add. Usage is implied by the posting semantics rather than spelled out.

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