Address Validator

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered, but the description adds substantial context beyond them: the cost model (0.02 USDC on Base, 1 validation), the x402 v2 payment path via params._meta and the X-PAYMENT header for v1 clients, and the meaning of a 200 with degraded=true (provider unreachable, incomplete response, low confidence). Payment and degraded-response semantics are exactly the kind of trait annotations cannot express.

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?

Three sentences, front-loaded with purpose and return shape, then the degraded case, then cost/payment. Nothing is padding, though the final payment sentence is dense with protocol detail and slightly compresses readability.

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?

With an output schema present, return values need not be enumerated, yet the description still conveys the key semantic output (deliverability class + confidence) and the critical failure mode (degraded=true). Combined with the payment requirement, an agent has what it needs to invoke this correctly; only edge cases such as retry/refund behavior on degraded responses are unaddressed.

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?

Top-level schema description coverage is 0%, and the description adds no semantics for the address fields (street/city/state/zip/country), which are largely self-evident and carry their own brief descriptions in $defs. It does add one genuinely useful parameter-level detail the schema lacks: where the payment payload must be placed (params._meta['x402/payment']). That partially compensates for the coverage gap, landing at the baseline.

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 names a specific verb and resource ('Valide une adresse de livraison') and immediately states what comes back: standardized form, coordinates, and a deliverability classification with confidence. No sibling tools exist, so no disambiguation is required, and an agent knows exactly what the call produces.

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?

Usage context is implied rather than stated: there is no explicit 'use this when...' clause or exclusion, though none is needed since there are no alternatives. It does give operational guidance for the degraded case, which indirectly tells the agent how to interpret results, but not when to prefer this tool over other approaches.

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