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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds behavior beyond them that matters a lot for a paid tool: per-action price tiers, payment rails (USDC on Base, Polygon or Solana), data freshness (index refreshed every 6 h, chain data real time), and the key billing guarantee that 'failed or empty calls are never charged'. That last clause directly answers the biggest risk an agent faces when calling a metered endpoint.

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?

Front-loaded with scope and then a tight action-by-action clause list; every sentence carries either a mode, a price, a freshness guarantee or a billing guarantee. Slightly dense with repeated price parentheticals, but there is no filler and the ordering (scope → modes → freshness → payment) matches how an agent needs the 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?

For an 11-parameter, 5-mode tool with no output schema, the description covers modes, cost, freshness, rails and failure billing, and hints at returns ('ranked by fit, price and trust', 'with a cursor', 'up to 3 hops'). What is not stated is the shape or granularity of each response beyond those hints — acceptable given the strong annotation and schema coverage, but a one-line note on return contents per action would close the gap.

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% and every property already names the action it serves, so the baseline would be 3. The description adds semantics the schema does not contain — the price attached to each action ('sets the price, see above') and the depth cap framing for counterparty traversal — which meaningfully reinforces parameter selection rather than repeating field definitions.

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 concrete verb and resource ('Answers about the x402 agent-payments market from the whole Bazaar index and Base chain history') and then enumerates all five actions with the specific question each answers: recommend, seller_check, payer_profile, seller_customers, payments_feed. No sibling tool covers x402 payments, so disambiguation is trivially satisfied, but the internal action enumeration makes each mode unmistakable.

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?

Each action is paired with the question it answers ('which x402 API to call for a need', 'is an x402 endpoint / seller trustworthy'), which functions as explicit when-to-use guidance, and the per-call prices give a cost-based selection signal. What is missing is guidance for overlapping modes: payer_profile vs payments_feed both take a wallet address, and seller_check vs seller_customers both take a seller, with the distinction left to be inferred from 'up to 3 hops' and 'in time order, with a cursor'.

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