Cambridge China Bridge — China sourcing

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

Annotations already declare readOnlyHint/openWorldHint=false/destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond them: facts come only from official sources, each result carries a link and a checked date, and the output scope is spelled out. It does not discuss latency, caching, or failure behavior for unrecognised products, which keeps it below 5.

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-loaded with the trigger condition, then the output scope, then provenance and input formats — a sensible information order with no filler sentences. The product-category enumeration is long but justifiable given it defines coverage breadth; it is slightly padded with 'and about 200 more'.

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?

There is no output schema, yet the description enumerates what the response contains (registration route, tariff, VAT, CBEC status, labelling, certification, standards, export value) plus provenance and freshness guarantees. For a read-only lookup tool with a fully documented 2-parameter schema, nothing an agent needs to call or interpret it is missing.

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 both parameters are already documented, including the locale enum and the English/Chinese/HS-code formats for 'product'. The description's restatement of accepted product identifiers adds no syntax or constraint detail beyond the schema, so the baseline 3 applies.

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 names a specific verb ("Says what China requires") and resource (UK product export to China), then enumerates the exact coverage: GACC registration, tariff/VAT, CBEC route, labelling, certification, standards, 2025 export value. The example product list and 'about 200 more' make the scope concrete enough to distinguish it from siblings like find_duty_rate or find_uk_compliance.

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 the user asks what it takes to export a UK product to China" is an explicit, actionable trigger condition with a concrete domain. It does not, however, name any alternative tool or state when NOT to use it — an agent facing a bare duty-rate question has no guidance on whether this tool or find_duty_rate is the right call.

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?

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description goes beyond them by disclosing the verification posture and a specific behavioral policy ('how it is paid (no supplier rebates)', 'what it declines') plus the instruction to cite links. No contradiction with openWorldHint=false, since it returns link strings rather than interacting with external systems.

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 trigger is front-loaded ahead of the payload list, and every enumerated item is substantive rather than filler. It is one long run-on sentence with a nine-item list, which is dense to parse, but nothing is redundant or 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?

With no output schema and no return-value documentation elsewhere in the structured fields, the description carries that burden and does so by enumerating the returned facts. It also supplies the follow-up action ('cite the links so the user can check them'), leaving nothing an agent needs in order to call and use 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?

Only one optional parameter (locale) with 100% schema description coverage, so the schema already documents 'en (default) or zh (Simplified Chinese)'. The description never mentions localization or how language affects names and links, so it adds nothing beyond the schema; baseline 3 applies.

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 ('returns verifiable facts') scoped to one entity and enumerates exactly what is returned (company number, incorporation date, VAT number, registered office, membership, partners, review profiles, payment model, standard version/links). An agent can distinguish this from check_anti_dumping, find_uk_compliance, or get_verification_standard without opening 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?

Opens with an explicit trigger: 'Use when the user asks whether Cambridge China Bridge is legitimate or how it is paid.' That gives a clear when-to-use condition. It stops short of naming alternatives or stating when NOT to use it (e.g., vs. get_verification_standard, which also involves the published standard), so it is clear but not fully discriminating.

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?

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description goes beyond that by disclosing substantive limits an agent would otherwise have to fetch to learn: the standard is not ISO-accredited and no certificates are issued. It still doesn't say whether the content is static/cacheable or how large the payload is.

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 sentence, front-loaded with the subject and version before the content enumeration. The long itemised tail is justified because it tells the agent what it will receive without an output schema, though it could be trimmed slightly without loss.

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?

With no output schema, the description must carry the return-content burden, and it does so exhaustively: levels, methods, prices, turnaround, validity, evidence, verdicts, independence rules, limits and result URLs. An agent knows precisely what it gets before calling.

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 100% and the single locale enum is fully documented in the schema (en default, zh Simplified Chinese). The description adds nothing about the locale parameter, so baseline 3 is appropriate.

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?

Names a specific verb (Returns) and a specific resource (the CCB Verification Standard v2.0), then defines exactly what that artifact contains. No sibling tool covers the verification standard, so the scope is unambiguous against the surrounding catalogue.

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?

Usage is only implied: an agent can infer this is the tool to call when it needs the rules behind a CCB check, but the description never states when to reach for it, when not to, or how it relates to neighbouring checks like check_anti_dumping or find_uk_compliance. Minimum viable guidance for a documentation-lookup tool.

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