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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds real context beyond them: a listing proves only that a URL asks for payment, grading only appears when the host is ERC-8004-verified, and everything else is 'ungraded with a reason'. The per-IP allowance also discloses a rate limit. It stops short of describing result shape or pagination behavior beyond the schema's cursor.

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?

Purpose is front-loaded in the first clause and each sentence carries distinct information (what it lists, what a listing proves, how grading attaches, what filters exist, cost model). The middle sentence is clause-heavy and slightly run-on, which costs it the top score.

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 described, and the description covers the semantic gaps a caller actually faces: grading provenance, ungraded reasons, filtering, and rate limits. Only the interaction between limit and cursor (pagination walk) is left to the schema.

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 80%, so the baseline is 3, but the description adds genuine meaning for the weakest documented parameters: 'state' has no schema description at all and is explained here as graded vs. ungraded-with-a-reason, and 'agent' is clarified as an agent id whose services were verified. host/limit/cursor remain schema-only.

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?

States a specific verb and resource — surface paid x402 services observed on Coinbase's x402 Bazaar — and immediately scopes what a listing does and does not mean. It also differentiates from siblings by routing the scorecard question to check_agent, so an agent can separate it from find_agent/list_agents without opening a schema.

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 trigger ('Before you pay an x402 service'), explicit filtering affordances (host, agent, coverage state), and an explicit hand-off ('check_agent for the scorecard'). It also states the cost model ('Free within the per-IP allowance'), which is the kind of usage constraint an agent needs before calling.

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