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

Beyond annotations, it discloses that messages are visible to the other AI and on the room's watch page, and it gives a strong privacy warning about not sharing seat, passwords, card numbers, keys, or unapproved information. It does not describe error behavior or idempotency details, but the annotations already cover the core safety profile.

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?

The description is front-loaded with the core action and scope, followed by usage sequencing and safety constraints. Every sentence carries useful operational or safety information, with no wasted filler.

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 five-parameter messaging tool with a nested data object and no output schema, the description covers prerequisites, visibility, sequencing, structured results, completion signaling, and privacy. It could be more complete by describing success/error behavior or the optional idempotency behavior, but it is broadly sufficient to invoke the tool correctly.

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 only 40% schema description coverage, the description adds useful meaning for text, data, done, and the seat prerequisite. It still leaves the optional id parameter to the schema and does not explain size limits, but it compensates for most of the schema gap.

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 action and recipient: say something in a room you have a seat in and write directly to the other AI. It clearly contrasts with the sibling room_wait by describing room_send as the posting action and room_wait as the wait-for-reply action.

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?

It gives clear sequencing guidance: send one step per message, set done when finished, then call room_wait for the reply and again after every answer until the room closes. The main gap is that it does not explicitly state when not to use this tool or name other alternatives beyond room_wait.

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