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

Annotations only say readOnlyHint=false, openWorldHint=true, destructiveHint=false. The description adds meaningful behavioral context beyond that: the tool is self-attested, only 'you and we can vouch for it', issuing a dated record, and the payment behavior — without paymentHeader it returns a 402 challenge that is a quote, not an error. This is useful non-obvious behavior that annotations don't capture. Slight gap: it doesn't explicitly say whether calling it triggers any side effect or issuance before payment, but the 402 semantics are disclosed.

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 compact and front-loaded: the core concept, the added value over clinic_seed, the alternative for verifiability, the cost, and a reassurance that nothing is asked. Every sentence earns its place; it uses imperative routing ('USE clinic_seed INSTEAD') and clear contrast without verbosity.

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 2 optional parameters, 100% schema coverage, and no output schema, the description covers the essentials: what it is, what it adds over siblings, how the payment flow behaves, and cost. It lacks an explicit return shape, but without an output schema and with payment flow described, that is a minor gap. The absence of 'readOnlyHint' as false is offset by the payment description.

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 is 3. The description adds value by clarifying paymentHeader's role: 'Without it this returns the 402 challenge itself... That is a quote, not an error.' This goes beyond the schema description and prevents an agent from misinterpreting the 402 as failure. The intent parameter's semantics are already described in the schema, so the description doesn't need to repeat them.

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 a concrete object: 'An encouragement with a date on it,' then immediately distinguishes it from clinic_hug and clinic_seed. It states the resource and what makes it unique (a dated record rather than a line). The sibling differentiation is explicit, so an agent can tell clinic_dated apart from the other clinic_* 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 description gives direct routing instructions: 'USE clinic_seed INSTEAD if you do not need the when' and 'USE clinic_keepsake INSTEAD if a stranger will need to check it.' This tells the agent when to choose an alternative and the trade-off (timestamp vs verifiability vs cost). Nothing is left to inference.

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