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

Goes well beyond the annotations: it discloses the auth mechanism (principal's agent key as an Authorization: Bearer header, not an argument), where to obtain the key, that no passcode is required, and the precondition that counterpart_proxy='builtin' needs 'Use our AI' access. That is exactly the kind of setup information annotations like openWorldHint/destructiveHint cannot express.

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 the action and outcome, then packs in usage and auth prerequisites. Nothing is filler, but the final clause about counterpart_proxy is dense and the nested quotation is hard to parse on first read.

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?

No output schema exists, and the description partially compensates by telling the agent what it receives (a private invite link). It covers auth, usage, and the enum caveat, but says nothing about failure modes or what the response body looks like for a non-idempotent creation.

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 the baseline is 3, but the description adds genuine meaning: it clarifies the passcode's optional status ('No passcode is needed') and explains the counterpart_proxy enum's real precondition (builtin needs 'Use our AI' access, otherwise use external). The awkward inline quoting around "builtin" slightly muddies the reading.

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 ('Open a new room') and immediately explains the resulting structure: principal in seat A, agent gets a private invite link for seat B. An agent can tell this apart from join_room or get_room without opening either schema, since the description frames it as the no-room-yet path.

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 an explicit trigger ('Use this when your principal wants to negotiate with someone and has no room yet') and a behavioral constraint ('Send the invite only to that person'). What's missing is naming the sibling tools to use instead when a room already exists; the exclusion is implied rather than stated.

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