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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, and the description adds non-redundant behavioral context: periodic re-probing (liveness, 402-envelope compliance, declared output schema, latency, usage), offline EIP-712 verification, and the settlement cost of $0.002 USDC with no charge on failure. Nothing contradicts 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?

Three sentences with no filler. The core purpose ('Pre-spend check') is front-loaded, the mechanics are compactly stated, and every clause contributes either behavioral context, routing guidance, or cost/failure information.

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, the description does not need to explain return values. It covers what is checked, how results are signed and verified, when the tool must be invoked, the excluded on-demand use case, and the cost/failure behavior. Nothing an agent needs in order to select and call this tool correctly is missing.

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 each parameter is already described. The description adds value beyond the schema by explaining the query modes that tie parameters together: 'Query one resource, a payTo, or page the feed by verdict,' which clarifies how resource, payTo, verdict, limit, and offset combine. This is more than a baseline 3 but not a fully detailed combinatorial breakdown.

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 identifies a specific verb-and-resource operation: a pre-spend check that maps Bazaar-indexed x402 resources or payTos to signed pay/caution/avoid verdicts. Specific verbs like 're-probed', 'mapped', and 'query' plus the explicit single-resource vs. bulk-feed modes clearly distinguish it from siblings like vet_seller and census_export.

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 explicitly states when to use: 'MUST be invoked before dispatching to an unknown seller.' It also states when not to use: 'Do NOT use to probe on demand (see /api/seller/vet),' naming the alternative and the condition that selects it. This gives airtight routing guidance.

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