agentcn

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to reiterate safety. It adds value by describing the return content (applicable/excluded/unresolved requirements, citations, reviewed outcomes), but does not disclose potential behavioral traits like response size, pagination, or error conditions.

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 consists of two sentences, but the second is a bilingual repetition of the first. While not verbose, the redundancy reduces conciseness. It is reasonably front-loaded but could be more succinct.

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 20 parameters and low schema coverage, the description should provide more context about input requirements and output. It mentions the return structure but lacks details on parameter relationships, prerequisites, or edge cases. The presence of an output schema reduces the burden, but the description remains incomplete for a tool of this complexity.

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?

With only 20% schema description coverage (4 of 20 parameters have descriptions), the tool description should compensate. Instead, it only generically mentions 'product attributes and target markets' without detailing any specific parameters. This provides little additional meaning beyond the schema.

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 conveys that this tool performs a rule-assessment for market-access compliance, returning applicable, excluded, and unresolved requirements. However, it does not explicitly differentiate itself from sibling tools like compare_market_requirements or describe_coverage, which limits its distinctiveness.

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 positions the tool as the 'rule-assessment layer' but offers no explicit guidance on when to use it versus siblings. There are no when-to-use, when-not-to-use, or alternative recommendations, leaving the agent to infer usage from the tool name and context.

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 and idempotentHint. The description adds context about the specific data fields compared (marks, duties, etc.), which goes beyond the annotations.

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?

Two concise sentences (bilingual) front-load the purpose. No wasted words, though the Chinese-first ordering might slightly delay English understanding.

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 gives an overview but lacks detail on how optional parameters affect the comparison. For a complex tool with 20 parameters, more context on parameter usage would be helpful. Output schema existence reduces the need for return value explanation.

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?

With only 15% schema description coverage, most optional parameters (e.g., age_group, battery_type) are unexplained in the description. The required parameters category and markets are implied but not detailed. The description does not compensate for the low coverage.

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 it compares market requirements across multiple markets, listing specific aspects like marks, local-presence duties, risk, sources, and outcome coverage. It distinguishes from siblings which focus on single-market assessment or other tasks.

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?

No explicit guidance on when to use this tool versus alternatives (e.g., assess_product_compliance for single markets). No when-not advice or prerequisites mentioned.

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, idempotentHint, and openWorldHint, so the safety profile is clear. The description adds behavioral context beyond annotations by detailing the specific information returned (versions, coverage, verification status, methodology), which helps the agent understand the tool's contribution and trust implications.

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 concise, consisting of two bilingual sentences. It is front-loaded with the primary function and purpose. The bilingual repetition adds slight redundancy but does not detract significantly from clarity.

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 tool has an output schema (not shown but signaled), so return value explanation is unnecessary. The description adequately covers what the tool does and why it should be invoked, making it complete for an agent to decide when to use it.

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 parameter (language) exists, with 100% schema coverage including enum values and default. The description does not add any additional meaning or usage details beyond the schema. Per guidelines, baseline 3 is appropriate when schema coverage is high.

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 what the tool does: returns dataset versions, category/market coverage, verification-status tallies, and editorial methodology. It also explicitly distinguishes its purpose from siblings by noting it should be called to understand data trustworthiness before relying on other tools, which are focused on different tasks like compliance assessment or market comparison.

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 provides explicit guidance on when to use the tool: 'call this to understand data trustworthiness before relying on other tools.' It implies a prerequisite context but does not explicitly state when not to use it or name direct alternatives among siblings.

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 indicate read-only and idempotent behavior. The description adds context by specifying the output includes evidence and verification status, which is beyond annotation disclosure. No contradictions found.

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 extremely concise with two sentences, covering both Chinese and English versions, and front-loads the core action. No unnecessary words.

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 output schema exists, the description need not detail return values, but it does provide useful specifics. The tool is simple with two parameters, and the description is sufficient for an agent to select and invoke it 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?

The description clarifies claim_id as a 'stable claim ID' and explains what it resolves to, adding meaning beyond the schema. However, the language parameter is not mentioned, and schema coverage is 50%, so the description only partially compensates.

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 resolves a stable claim ID to its text, primary-source evidence, verification date, and editorial evidence gap. It distinguishes itself from sibling tools like assess_product_compliance by focusing on explaining a specific claim rather than assessing or comparing.

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 implies use when needing details about a claim's evidence, but it does not provide explicit guidance on when to use this tool versus alternatives, nor does it list when not to use it.

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 and idempotentHint=true, so the description adds context about the data being 'editorially reviewed' and 'anonymous', which is useful beyond the annotations. No contradiction exists. The description does not disclose potential rate limits or pagination, but the safety profile is well-covered.

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 concise—two sentences covering both Chinese and English—with no unnecessary words. It front-loads the key action and provides illustrative examples. Every part contributes to understanding.

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 tool has 6 parameters (all optional with enums) and an output schema exists, the description gives a general idea of what outcomes are returned but omits details on filtering or parameter usage. It is adequate for basic understanding but leaves gaps for an agent needing to construct precise queries.

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?

With only 17% schema description coverage (only 'language' has a description), the description fails to compensate. It lists example outcomes but does not explain how parameters like limit, market, result, category, or checkpoint affect results. The schema provides enums but no semantic guidance, and the description adds minimal value.

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 it finds editorially reviewed anonymous outcomes, listing examples like evidence requests and customs holds. The verb 'find' and the Chinese translation make the purpose explicit. While it differentiates from siblings (which focus on compliance assessment and requirements), it does not explicitly contrast with them, so a score of 4 is appropriate.

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 provides no guidance on when to use this tool versus alternatives like assess_product_compliance or describe_coverage. An agent would need to infer usage from context alone. No when-not-to-use or alternative recommendations are given.

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 indicate readOnlyHint=true, idempotentHint=true. The description adds that the tool generates drafts only and does not provide approvals or legal opinions, confirming its non-destructive, informational nature. It also details the scope (stage two, same product profile) which is beyond the annotations.

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 concise, with two short paragraphs (Chinese and English) that front-load key information (stage, prerequisite). Every sentence adds value. It could be slightly more compact, but overall it's efficient.

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 tool's complexity (25 parameters, many enums), the description provides a high-level overview but lacks detail on how the four routes map to parameters or what the output schema contains. The presence of an output schema reduces the need to describe returns, but the description could still be more complete in tying parameters to the workflow.

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 only 24%, so the description bears a heavy burden to compensate. However, the description does not explain any parameters beyond saying 'same product profile and preflight gap'. It does not clarify the required parameters (category, markets) or optional ones. Given the low coverage, this is insufficient.

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 is stage two of the ComplianceCN market-access check, specifying it must be called after preflight_product. It lists the four routes and the generated outputs (supplier file requests, lab briefs, etc.), and explicitly distinguishes itself from approval, certification, or legal advice. This differentiates it from siblings like preflight_product or assess_product_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?

The description explicitly states when to use: 'call after preflight_product'. It implies the tool is dependent on having completed the preflight step. It does not list explicit alternatives or when-not-to-use scenarios, but the context of sibling tools and the clear sequencing provide adequate guidance for a specialized tool.

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?

The description adds significant behavioral context beyond the annotations (readOnlyHint, idempotentHint). It explicitly states the output is non-binding, suggestions are advisory, and only the source-linked evidence_checklist is authoritative. It also clarifies that no compliance approval is returned. This meets a high threshold given the annotations already indicate a read-only, idempotent operation.

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 succinct: two sentences (one Chinese, one English) that front-load the purpose and key differentiator. No extraneous information. Every part 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?

Given the tool's complexity (25 params, 2 required) and the presence of annotations and output schema, the description is sufficiently complete for an AI agent to understand the tool's purpose, behavior, and output nature. It could be improved by linking to the sibling tools more clearly, but the core is covered.

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?

With only 24% schema description coverage and 25 parameters, the description does not elaborate on parameter usage or constraints beyond the schema's basic descriptions. It does not compensate for the low coverage by explaining which parameters are needed for different scenarios or how they affect the output.

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 identifies the tool as a preflight check: it generates evidence lists, gaps, next steps, trust states, and non-binding suggestions, and explicitly states it never returns a compliance approval. This distinguishes it from the sibling tool 'assess_product_compliance' which likely provides a compliance verdict.

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 positions this as 'Stage one' of a compliance check and emphasizes it is not a compliance approval, implying it should be used for initial screening before a full assessment. However, it does not explicitly mention when to use sibling tools like 'compare_market_requirements' or 'explain_claim', leaving some ambiguity.

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 indicate mutability and non-idempotency. The description adds behavioral context: creates a private lead, never accepts document uploads, and returns a reference. No contradiction with annotations.

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 a single, well-structured sentence that front-loads the core purpose and includes key usage constraints without extraneous detail.

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 tool's complexity (5 params, nested objects) and existence of an output schema, the description covers the handoff context, prerequisites, and behavioral notes. It is complete enough for an agent to use correctly, though it could briefly mention the return value.

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 adds value by warning about not including document contents in the message field, emphasizing the need for consent on contact, and clarifying product_profile reuse. This goes beyond schema descriptions.

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: an agent-callable handoff from automated preflight to human review for ComplianceCN Check. It distinguishes from siblings by specifying post-preflight usage and constraints like creating a private lead and not accepting document uploads.

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 explicitly states when to use: after preflight_product reaches a review gate or user requests human review. It also gives constraints such as requiring consent and no document uploads, but it does not explicitly list alternative tools for other scenarios.

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