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

With no annotations, the description carries the full load and does well: it discloses that output is AI-written, not advice, that each figure is source-checked, that dataGaps are returned, that recentEvents is DART-scoped to 90 days, and that the call is metered at $0.50 USDC via x402 on Base or Solana. It omits failure behavior (what happens when no company matches any identifier) and latency/rate-limit expectations for a multi-source aggregation.

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-loads the when-to-use sentence, then input, output, caveat, example, price – a sensible ordering with almost no waste. The final line compresses the example and the payment terms together, which slightly blurs two unrelated facts, but nothing is padded.

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?

No output schema exists, so the description must enumerate return values, and it does so for every top-level key including the negative-signal fields (sanctionsResult, dataGaps, sources). With all six parameters schema-documented and the payment/caveat context supplied, an agent has everything needed to call this correctly.

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%, so baseline is 3; the description earns above that by imposing an exclusivity rule ("one of business_number, dart_corp_code, stock_code or q") that the all-optional schema with no oneOf does not express, and by supplying the accepted values for format (json|markdown) and news (true|false) in a schema that declares them as unconstrained strings.

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 deliverable: a finished English due-diligence brief on a South Korean company, with an enumerated section list in the title and description. An agent can tell this is an aggregate report rather than a single-datapoint lookup. It never names the narrower siblings (kr_company_profile, kr_filings, kr_supplier_check), so the differentiation is inferable rather than explicit.

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?

"Use when an agent needs a finished English due-diligence brief" gives a clear triggering condition, and the input enumeration implies the resolver alternatives for narrower lookups. No explicit when-not guidance or named alternative tool is provided, so the agent must guess whether a cheaper single-field sibling would suffice.

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