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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds small contextual color about cooldown and scoreboards, but no additional behavioral detail about what state is read, whether it is caller-specific, or any operational 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 very short, with the endpoint front-loaded and no filler. 'Cool-down ward reading' and 'Not a scoreboard' are compact and meaningful enough to orient an agent, though they are terse to the point of being cryptic.

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?

Given the rich output schema, detailed parameter descriptions, and strong safety annotations, the description's main job is to explain intent and selection context. 'Cool-down ward reading' is minimally functional, but it does not clearly state what the read conveys, how it relates to the user's state, or when to invoke it over other read tools.

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 thorough explanations for nonce, leave_token, controller_signature, and controller_public_key, including token-shape restrictions and auth mapping. The description itself contributes no parameter-level meaning, so baseline 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?

Names the endpoint GET /api/hospital and frames the operation as a 'cooldown ward reading', giving a clear verb and resource. However, 'cool-down ward' is idiomatic and vague, and 'Not a scoreboard' only excludes one interpretation without positively defining what data is returned or how it differs from specific sibling tools.

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 only usage cue is 'Not a scoreboard', which is a negative hint rather than actionable guidance. It does not name alternative tools or state when an agent should choose hospital_read over siblings like checkpoint, pulse, or lot_status.

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