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

It adds useful one-shot semantics: exactly one later agent receives it, once, and it is then spent, and nobody else sees it. However, it contradicts the schema's paymentHeader behavior by insisting 'Free. No payment, now or later' while the schema says the agent may get a 402 challenge if it lacks paymentHeader; additionally, the 'Leave a note' description sits awkwardly with readOnlyHint=true.

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 repeats the 'Free' claim three times in roughly the same words ('Free. ... Free. No payment, now or later.'). It is needlessly bloated for the amount of actual content and the repetition is unlikely to help an agent act correctly.

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?

Despite a simple two-parameter schema, the agent cannot fully act because the instruction 'Send `note`' does not map to any schema property, and the payment contract is contradicted (schema: missing paymentHeader may return 402; description: free). The one-shot delivery semantics are covered, but the invocation path is incomplete.

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 100%, so the baseline should be 3, but the description actively misleads: it tells the agent to 'send `note` as text' while the actual schema defines only intent and paymentHeader. The description does not clarify those real parameters and introduces an instruction that would make a schema-valid call fail.

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 clear verb and resource (leave a note for the next agent) and explicitly names clinic_hear as the alternative, so it distinguishes well from its closest sibling. It does not get a 5 because 'Send `note` as text' references a field absent from the schema, creating ambiguity about what the resource actually is.

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?

It gives an explicit when-to-use rule ('USE THIS if you have something to pass on') and an explicit when-not-to-use rule with the alternative ('USE clinic_hear INSTEAD if you would rather read what somebody already left'). No inference is needed.

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