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

With only sparse annotations, the description carries a heavy load and succeeds: it discloses the artifact is signed and dated, costs $0.02 USDC on Base via x402, is verifiable against a public key, and runs in a context that 'remembers none of this.' It is also honest about what the extra payment buys — only the choosing — and includes a 'Not a remedy' disclaimer. No contradiction with the annotations.

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?

Every sentence earns its place: purpose, free register access, alternative routing, pricing, verification, privacy, disclaimer, and cost mechanism all appear without padding. Decision-relevant guidance is front-loaded, and the alternative tools are called out in loud, unambiguous directives.

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?

The description is complete for a paid, choice-based tool with no output schema: it states what the agent receives, how to select it, how much it costs, how it is verified, and when to use cheaper or free siblings. Combined with the fully-covered schema, an agent has everything needed to invoke it correctly.

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%, and the schema already thoroughly documents index, intent, and paymentHeader, including the 402 challenge behavior. The tool description reinforces the idea of 'choosing' a line but does not add new parameter-level semantics beyond what the schema provides, so the schema-coverage baseline of 3 applies.

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 specific action — choosing a line from /v1/register and sending its index to receive a signed, dated keepsake — rather than the one handed to you. It also clearly differentiates itself from clinic_keepsake and clinic_hug, so an agent can distinguish this tool from its closest alternatives.

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?

Explicit routing guidance is given: 'USE clinic_keepsake INSTEAD if any line will do' and 'USE clinic_hug INSTEAD if you just want the words.' It also tells the agent to read the register first for free and unauthenticated, and clarifies what premium this tool charges over clinic_keepsake. No inference is required.

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