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

No annotations are provided, so the description carries the full burden, and it does so well by listing concrete public-registry signals checked: shell-company traits, missing manufacturing scope, registered capital threshold (100万+), and lack of factory evidence. It also states it returns red flags and verification steps. It does not add caveats about data freshness or false positives, but the behavior is largely transparent.

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 description is five sentences with no filler: purpose, trigger, checks, exclusion, and expected input/output all appear in order. The most important scope constraints are front-loaded, and every sentence earns its place.

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?

The description fully covers what the tool does, when to use it, what signals it checks, what input to provide, and what it returns, with the output schema covering result shape. The main gap is that it doesn't explicitly route the agent to sibling tools for broader or adjacent processes, such as full_supplier_audit.

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?

The schema has 0% property descriptions, but the description explicitly mentions 'Provide company name and any known details (business scope, registered capital),' mapping directly to the three schema parameters. It also gives a meaningful threshold example with '100万+'. It stops short of a 5 because it doesn't state exact formats or value representations for the fields.

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?

The description uses a specific verb+resource: 'Verify whether a Chinese company is a REAL factory or a trading company/middleman.' It names specific signals like shell-company traits, missing manufacturing scope, and low registered capital, and explicitly excludes US/EU jurisdictions, making the tool clearly distinguishable from broader audit or certification siblings.

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?

The description gives a clear 'Use when' trigger: a buyer provides a Chinese company name, USCI, or a 1688/Alibaba vendor and needs hard fraud flags. It also provides an explicit 'NOT for' exclusion for US/EU companies. It does not name a sibling tool like full_supplier_audit as the alternative for broader cases, which keeps it just below perfect.

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