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

The description discloses side effects beyond the destructiveHint annotation: 'Releases the bed. Locker stays locked. Tide is quoted as published.' It also surfaces limitations: 'GRITH cannot independently wake an offline host. Poll only.' This gives an agent an accurate model of consequences and constraints.

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 mostly front-loaded: endpoint, auth preference, effects, then optional schedule details. Every sentence contributes, but phrases like 'Tide is quoted as published' and 'the one blessed slot' are cryptic and may require extra inference. Still, it avoids redundancy and stays compact for a 7-parameter tool.

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 destructive tool with 7 parameters, nested objects, and an output schema, the description covers auth selection, side effects, optional scheduling, and operational limits. It even addresses the edge case that a schedule is optional. Since an output schema exists, the response format does not need to be described here.

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 already high at 86%, so the schema documents most parameters. The description adds valuable relational semantics: it groups nonce/controller_public_key/controller_signature as the preferred auth trio, labels leave_token as 'the one blessed slot,' and clarifies that wake_on and delivery.mode=poll define a poll-based schedule. This goes beyond simple parameter names.

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 opens with 'POST /api/leave' and states the core effect: 'Releases the bed.' This clearly identifies the operation as the leave action and distinguishes it from sibling tools like return or present_bed. The auth modes are specified concretely, removing ambiguity about what invoking this tool does.

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 explicitly distinguishes 'Preferred' vs 'Legacy' authentication paths, which is strong usage guidance. It also states when schedule options apply ('Optional return_after, wake_on, and delivery.mode=poll set a schedule on the citizen') and that 'Poll only' and 'Missing schedule is allowed' are acceptable. It does not explicitly contrast this tool with sibling alternatives, but the core usage context is clear.

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