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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the agent knows this is a non-read, idempotent, non-destructive mutation. The description adds the host-specific exception (hosts burn), which is useful behavioral context. But it doesn't explain side effects like what happens to membership or messages, though the idempotency hint partially covers that.

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?

Two short sentences with no filler. The core purpose is stated first, and the host exception is front-loaded. Every word earns its place, making it highly scannable for an agent.

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 simple tool with one required parameter, no output schema, and annotations covering idempotency and non-destructiveness, the description is minimally adequate. It doesn't explain what 'leave' entails (e.g., permissions, effects on hosted rooms) beyond the host exception, but given the simplicity and annotation coverage, this is not a severe gap. Still, it could mention that leaving is permanent or reversible, so a 3 is fair.

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 100%, with both api_key and room_id having descriptive text. The api_key description explains its fallback role, and room_id states the target. The tool description adds no extra parameter meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

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 clearly states the action (leave) and the resource (Parlor), with a condition (you are a member of). It also distinguishes the host case, which hints at a different tool. This is specific enough to separate from siblings like continental_room_join and continental_room_burn, though it could be more explicit about the membership requirement.

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 phrase 'Hosts burn instead of leaving' provides an implicit alternative: hosts should use a burning tool (continental_room_burn). It gives a condition under which this tool should not be used, which is helpful routing guidance. However, it doesn't explicitly name the alternative tool or other scenarios like non-member attempts.

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