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

Goes well beyond the annotations: discloses the output contract (0-10 score, per-category findings, red flags), the epistemic limit (analyst reasoning over supplied details, no filings/news/breach database retrieval), provenance guarantees (AI-generation disclosure plus verifiable content hash), and a genuine cost/refund policy (refuses with no charge; $99.00 USDC per call via x402). The billing and refusal semantics are exactly the kind of side-effect detail that readOnlyHint=false and openWorldHint=true alone cannot convey. There is mild tension between "does not retrieve filings, news" and the web-source fetching precondition, but it is a scope refinement rather than a contradiction of 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?

Front-loaded with the value proposition and lens breakdown before pricing and caveats, and nearly every clause carries decision-relevant information (scope limits, hash, refund condition, price). It is dense to the point of being a single run-on block, and the pricing parenthetical could be hoisted, but no sentence is filler.

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 no output schema, the description carries the return-value burden and does so — score scale, per-category findings, red flags. Combined with the disclosed data limitations, the provenance hash, and the refusal condition, an agent has enough to decide whether to call this, what to put in `task`, and what it will get back for $99.

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?

Only one parameter, `task`, and the schema already describes it at 100% coverage as "Task/query text for this SKU". The description adds the useful implication that the vendor details must be supplied in that payload ("the vendor details you supply"), but it never states the expected formatting, required vendor fields, or what happens with an underspecified task — so it does no more than marginally exceed the schema.

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 ("Structured vendor risk assessment") and enumerates the four lenses covered: financial health, security posture with OWASP ASI01-10, adverse media/litigation, and supplier reputation. It explicitly distinguishes itself from the nearest sibling by pointing to security.massat-audit for live agent-system audits, so an agent can route correctly without opening either 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?

Gives explicit when-not guidance ("For an automated audit of a live agent system, see security.massat-audit") and states a hard precondition for execution: refusal when ≥5 web sources including the vendor's published terms cannot be fetched. What it lacks is any routing note for the obviously related siblings in the same namespace, notably bundle.vendor-vetting and procurement.council/trust-layer, which an agent would need to disambiguate a multi-step vendor workflow.

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