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

The annotations already declare openWorldHint=true, readOnlyHint=false, and destructiveHint=false, so external fetching and mutation-adjacent behavior are partly covered. The description genuinely adds value beyond them by disclosing the refusal/chargeless-failure policy tied to a concrete source threshold (≥5 web sources + registry/EDGAR) and the $1.00 USDC x402 price. However the refusal sentence is duplicated almost verbatim, and nothing is said about latency, partial results, or what happens on a partial fetch (4 of 5 sources).

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?

The refusal policy is stated twice in near-identical sentences, which is pure waste in a description this short. The scope list is well front-loaded, but the duplication makes the definition read as unedited and slightly undermines confidence in the threshold semantics.

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 open-world, multi-domain scan with no output schema, the description should say roughly what comes back (report, score, red-flag list) and how to choose it over sibling bundles; it does neither. Cost and the failure/refund condition are covered well, which offsets some of the gap, but an agent still cannot predict the response shape.

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?

There is a single optional parameter whose schema description ('Task/query text for this SKU') already reaches 100% coverage, so the schema carries the parameter burden. The tool description adds no guidance on how to phrase the task, what entity identifiers are expected, or how query specificity affects the ≥5-source threshold. Baseline 3 is appropriate given full schema coverage.

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 composite operation with an enumerated scope: financials, litigation, key personnel, IP, media sentiment, red flags. An agent can tell this is a bundled due-diligence scan rather than a single-source lookup. It stops short of naming the sibling it is not (bundle.due-diligence, procurement.vendor-vetting, agent.prehire-check), so the boundary between similar offerings is left implicit.

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?

There is no when-to-use or when-not-to-use guidance, and no reference to any alternative among the many overlapping siblings (bundle.due-diligence, bundle.vendor-vetting, procurement.vendor-vetting). The only conditional text is a failure/refusal policy, which is behavioral, not usage-routing.

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