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

With no annotations, the description carries the full burden and does substantial work: it discloses the paid x402 gate ($9 USDC, eip155:8453), async fallback with job_id plus a free result_url, and a 24 h cache — all non-obvious operational behavior. Gaps remain: no mention of what happens on payment failure, invalid domain, or partial-source failure, and no indication of idempotency.

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?

A single dense block with zero filler; the cost and payment rail are front-loaded so an agent sees the gating condition before anything else. Telegraphic compression (colons, semicolons, brackets) trades readability for information density but every clause carries distinct signal.

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?

Given six optional-heavy parameters, no output schema, and no annotations, the definition covers what an agent actually needs: what it returns (Markdown report, signed evidence hash, tri-state verdict), how it is paid for, and how to handle a slow response. Return values are described inline because no output schema exists, which is the correct compensation.

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%, including per-parameter notes and an enum for 'market', so the baseline is 3. The description adds essentially nothing beyond the schema — its parenthetical echoes ('recalls', 'EU-Ready + offer') restate what the individual parameter descriptions already say, and it never explains interaction between gtin/query/product_url/seller.

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+resource ('Readable vendor due-diligence report') and enumerates the evidence dimensions it aggregates (reputation, sanctions, recalls, EU-Ready, email auth, product offer) plus the output shape (Markdown, signed hash, proceed/review/block verdict). The listing implicitly reveals it is an aggregate of several sibling checks, but it never names the siblings it supersedes (vendor_due_diligence, trust_trio, sanctions_screen), so an agent must infer the boundary itself.

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 is only implied: the bundle of covered dimensions suggests 'use this for a one-shot full vendor assessment' and the async/caching notes hint at latency/cost tradeoffs. There is no explicit when-to-use, when-not-to-use, or pointer to the cheaper single-purpose siblings an agent should prefer if it only needs one check.

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