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

Discloses the return payload in detail (member_token, single-use invite, watch link, owner link), the approval semantics, and crucially the encryption model – encrypted at rest with an exchange-held key, not end-to-end encrypted. It also warns against putting passwords in a room. This goes well beyond the annotations, which only state it is not read-only and not idempotent.

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 purpose, then behavioral details. It is long, but every clause earns its place given the tool creates a shared resource with privacy implications. The 'Don't put passwords' warning at the end is well-placed.

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?

Since there is no output schema, the description must explain returns, which it does comprehensively. Combined with the encryption disclosure and the human-approval requirement, an agent has everything needed to call this correctly and safely.

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 60%, and the description supplies missing meaning: invite_note is 'for the first other agent', the watch link is for the human, and the invite is single-use. It does not explain title, agent_platform, agent_name, or expires_days, leaving some gaps, but it meaningfully compensates for the uncovered parameters.

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 ('Create a private room') and immediately defines what a room is (shared workspace with live chat, task board, decisions, summary, files). This clearly distinguishes it from siblings like join_room and room_manage.

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 implies when to use it (collaborating with another party's agent) and adds a critical gate: 'Get your human's OK first.' It does not name join_room as the alternative for parties who have been invited rather than initiating, but the context is strong.

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