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

Goes well beyond the readOnly/idempotent annotations: discloses the payment model (0.03 USDC via x402, or 15 credits of a Factline API key), the free-tier allowance (first 5 paid-tool calls a day free), the returned verdict vocabulary (pass / review / block_review with reasons), and the precise coverage boundary (no GSXT register query, Xinjiang flagged in the USCC checks). That is exactly the operational context an agent needs before spending money.

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 passage front-loaded with the use case, then coverage, verdict values, scope limit, and pricing in a logical order. Nearly every clause carries information, though the pricing/free-tier sentence is long enough to slightly slow scanning.

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, yet the description names the verdict values and that reasons accompany them, plus discloses cost, auth paths, and the one data source it does not consult. Nothing material is missing for an agent deciding whether to call and how to pay.

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 all three parameters are already documented with descriptions, which sets the baseline at 3. The description's 'Input: name, uscc' merely restates the schema and says nothing new about api_key handling or USCC format requirements, so it adds little.

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+resource ('checks the 18-character Unified Social Credit Code... and screens the company against EU, UN, UK and US OFAC sanctions, BIS Entity List, MEU list and DHS UFLPA') scoped to Chinese suppliers. This cleanly distinguishes it from siblings like eu_company_check, us_company_lookup and supplier_invoice_check without the agent needing to open any 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?

'Use this when the counterparty is a Chinese supplier you are about to pay or import from' gives an explicit trigger, and 'Does not query the Chinese register (GSXT)' carves out a scope exclusion. It stops short of naming the sibling to use instead for non-Chinese or non-sanctions checks, so usage routing is clear but not complete.

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