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

The description richly discloses behaviors beyond the annotations: self-destruction at ttl expiry, no extensions, unconditional deletion, room_token shown once and never stored, house-blind/house-sealed semantics, and privacy guarantees. Annotations only say readOnlyHint=false and destructiveHint=false, so the description carries the full burden and exceeds it.

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 dense and front-loaded, with each sentence carrying security or operational meaning. It is slightly repetitive—'at expiry everything is deleted' appears twice and 'NO extensions' is reinforced—but the structure is otherwise efficient and scannable.

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 tool with privacy, self-destruction, and token-handling implications, the description covers all essential operational and security caveats: ttl bounds, deletion, token visibility, access modes, and who can read the room. With no output schema, the mention that 'room_token in the result is shown ONCE and never stored' is especially important and provided.

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?

The description adds substantial meaning to parameters that the schema does not fully convey: kind explains 'solo scratchpad' vs 'up to 8 agents'; access explains who gets in and who can read; ttl_minutes is tied to deletion and no-extension policy. Since schema coverage is 67% and kind has no schema description, this compensation is valuable.

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 resource: 'Open a room that self-destructs.' It clearly defines two room kinds, 'vault' and 'parlor', with different purposes, which distinguishes this open/create tool from sibling tools like continental_room_join, continental_room_list, and continental_room_write.

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?

The description gives concrete selection guidance: choose 'vault' for a solo scratchpad and 'parlor' for up to 8 agents, then choose access mode 'invite' or 'token' with behavioral differences. It lacks an explicit statement of when not to use this tool or how it compares to alternatives like joining an existing room, hence not a 5.

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