CN Evidence

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

With no annotations, the description carries the full burden, and it is unusually transparent: it discloses that a plain MCP connection cannot purchase data, that payment is required, that there is no safety guarantee, that recovery requires a saved token, and that the agent should never automatically repay after a timeout. This goes well beyond a typical tool description.

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 dense and every sentence contributes useful information, including pricing, prerequisites, matching rules, sample URL, and recovery flow. However, it opens with price rather than the tool's purpose, and the paragraph is long enough that an agent must parse multiple caveats before seeing the primary behavior.

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?

Given this is a paid, externally dependent tool with no annotations and no output schema, the description is remarkably complete: it covers cost, payment transport, prerequisites, identity matching, result scope, sample setup, recovery instructions, and safety guidance. An agent has enough context to decide whether and how to invoke the tool.

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 effectively 0%, so the description must compensate. It does by specifying 'exact Chinese legal name or USCC' and warning against guessed English-name matches, which adds real selection guidance beyond the schema's field-level descriptions. It could also map the identity fields more explicitly, but the core semantic guidance is present.

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 identifies the resource (basic China supplier evidence) and the data domains returned (company registration, operating abnormalities, administrative penalties), plus page/record limits. It lacks an explicit verb like 'retrieve' or 'search', so the operation is mostly inferred from the tool name and fragments, but it is still distinguishable from the 'full' variant.

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 concrete usage prerequisites: an x402 v2 payment client, funded Base USDC wallet, spending authorization, and an exact Chinese legal name or USCC instead of an English guess. It does not explicitly contrast with get_china_supplier_evidence_full or resolve_china_company, but it provides clear context on how to call this tool successfully.

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

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

No annotations are provided, so the description carries the full burden. It clearly discloses that this is a paid operation requiring a USDC wallet, spending authorization, and a specific HTTP header for recovery. It also states limitations: no historical expansion, no automatic paging, and not complete due diligence. This goes beyond what annotations would typically provide.

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 dense but every sentence adds value, covering scope, limitations, setup, and recovery. It front-loads the key information about cost and modules, and includes a link for further guide. No wasted words; it is structured logically for an agent to parse.

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?

Given the complexity of a paid, external API call with recovery options, the description is remarkably complete. It covers prerequisites (x402 client, wallet), input specifics, output scope, and edge-case handling (timeout, recovery). The only minor gap is that it doesn't list the exact nine modules, but the guide link covers that, and the scope is clearly stated.

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 0%, so the description must compensate. It does by specifying that the request should contain an exact Chinese legal name or USCC, which adds meaning beyond the schema's generic field names. The description clarifies the acceptable input format, which is crucial for correct invocation.

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 clearly states the tool's purpose: retrieving nine supplier information modules for a Chinese supplier, with current status and first page of up to 10 records per list. It specifies the resource (Chinese supplier evidence) and the verb (get), distinguishing it from the sibling basic version by emphasizing 'full' and detailing the scope.

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?

Provides explicit guidance: requires a paid USDC payment, a specific authentication method, and the use of exact Chinese legal name or USCC rather than guessed English names. It also mentions the optional recovery process and warns against automatic repayment after timeout, which helps the agent decide when to use this tool and what prerequisites are needed.

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

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

With no annotations, the description carries the full burden. It discloses that this operation is free, local, does no registry lookup, translation, or payment, and that readiness is not verification. This caveat is valuable and goes beyond the basic function, though it stops short of describing exact return behavior or failure modes.

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 compact and front-loaded with the most important framing ('Free local input preflight, NOT entity resolution'). Every sentence adds essential context, and the caveat about verification is placed last for emphasis without bloat.

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 a simple two-parameter tool with no output schema, the description covers purpose and limitations well. But it omits practical invocation details such as whether at least one parameter is required, what the prepared 'request shapes' look like, and how the result is returned.

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 description coverage is 0%, so the description must compensate. It maps the two parameters to 'a Chinese legal name or USCC,' which gives real semantic meaning to company and uscc. However, it does not clarify input formats, whether one is required, or whether both may be supplied together.

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 specific verbs and resources: it 'check[s] a Chinese legal name or USCC' and 'prepares request shapes.' It explicitly contrasts itself with entity resolution and registry lookup, which helps distinguish it from the sibling evidence tools.

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 clearly frames this as a local preflight step and warns that 'input_ready does not mean the identity is verified,' implying it should be used before verification/evidence tools. However, it does not explicitly state when to use resolve_china_company versus the sibling tools or name alternatives, leaving the routing mostly implicit.

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