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 describes the tool as a read-like extraction (no mention of side effects), but it does not disclose potential behaviors such as handling of invalid images, privacy considerations, or whether it supports retries. The description is adequate but not comprehensive.

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 two sentences long, with the first sentence stating the core purpose and the second listing use cases. No wasted words, front-loaded, and easy to parse quickly.

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 simplicity (one parameter, no output schema), the description adequately covers purpose and usage context. It does not describe the return format, but 'extract number and expiry date' implies the output. The lack of failure-mode details is a minor gap.

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% for the single parameter 'image', which already details accepted formats (path, URL, data URL, base64). The description adds no additional meaning beyond the schema; it does not explain best practices or constraints for the parameter. Baseline 3 is appropriate as schema carries the load.

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 ('extract') and resource ('bank card number and expiry date from a bank card front image'). It clearly distinguishes from sibling tools like id_card_ocr or driver_license_ocr by focusing on bank cards.

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 best-use workflows ('payment binding, card-information prefill, bank-account verification'), providing clear context for when to use this tool. However, it does not mention when not to use it or suggest alternative tools, so it misses a small opportunity for completeness.

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 correctly states that the tool extracts fields (read-only behavior) and which page is supported. However, it does not disclose potential side effects (none expected) or performance characteristics, nor does it mention error scenarios for poor-quality images. This is adequate but could be improved.

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 sentences. The first sentence states the purpose and output, the second provides usage context and a limitation. Every sentence adds value, no fluff.

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 one-parameter OCR tool with no output schema, the description covers the key points: what fields are extracted, use cases, and a limitation. It could optionally describe the output format more precisely or mention error handling, but it is reasonably complete.

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%, so the baseline is 3. The description does not add any information about the 'image' parameter beyond what is already in the schema. It lists extracted fields but does not elaborate on parameter usage or constraints.

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 extracts structured fields from a Chinese driver's license main page, naming specific fields (license number, name, etc.). It distinguishes from sibling tools by specifying the document type and noting that the supplementary page is not supported, making the tool's purpose unambiguous.

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 use cases (auto insurance, car rental, etc.) and a clear limitation (supplementary page not supported). While it does not name alternative sibling tools for other document types, the context is sufficient for an agent to decide when to use this 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?

With no annotations provided, the description covers input formats, suggested thresholds, and calibration need. However, it does not disclose potential side effects, auth requirements, or behavior on failure (e.g., no face found). Adequate but not exhaustive.

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 two sentences with no wasted words. It front-loads the core function, then lists use cases, input support, and a business rule. Highly 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 no output schema, the description mentions the similarity score range and use cases. It provides input format details and threshold guidance. Missing error handling or response structure, but overall sufficient for a simple comparison 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 100%, so the schema already describes each parameter. The description restates input formats but does not add new parameter-level details (e.g., does not elaborate on sourcePhotoType enum). 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?

The description clearly states the tool compares two face photos and returns a similarity score from 0 to 100. It specifies the resource (face photos) and action (compare), and distinguishes from siblings like liveness detection or OCR 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 provides explicit use cases (customer onboarding, duplicate-account checks, selfie-to-ID matching) and a suggested business rule for decision thresholds. It does not mention when not to use or list alternative tools, but the context is clear.

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 must cover behavioral traits. It explains what fields are returned per side but does not disclose image requirements, error handling, or authentication needs. The read-only nature is implicit but not explicitly stated.

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 well-structured sentences. The first sentence states the core purpose, and the second sentence adds detail and use cases without 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 simplicity of the tool (2 parameters, no output schema), the description adequately covers the return fields for each side. However, it could be more complete by mentioning the output format (e.g., JSON object) and any image constraints.

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 the description adds limited parameter-level meaning beyond the schema. The 'side' parameter's enum values are described, but no additional detail about the 'image' parameter is provided beyond what the schema already states.

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 extracts structured data from a Chinese national ID card, specifies front and back side fields, and lists use cases. It distinguishes itself from sibling OCR tools for other document types.

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 context by stating best-fit use cases (identity-data prefill, document digitization, onboarding automation). However, it lacks explicit guidance on when not to use this tool versus alternatives like driver_license_ocr or bank_card_ocr.

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 exist, so the description must fully disclose behavior. It reveals that the tool uses an async upstream job that is automatically submitted and polled, which is critical for an agent to handle correctly. It also lists many label codes, giving a detailed view of what the tool detects.

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 relatively concise, with the main action in the first sentence and supporting details following. It avoids redundancy, though the list of labels could be slightly more compact. Overall, it's well-structured and front-loaded.

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 explains the purpose and async behavior, but does not describe the return value structure (e.g., whether it returns presence flags, confidence scores, or raw labels). Given the absence of an output schema, this omission reduces completeness for an agent needing to interpret results.

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 grouping label codes into portrait and environment categories and providing an example, which helps the agent construct valid input beyond the schema's bare 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 verb 'Analyze' and the resource 'image/video for risk and scene attributes', listing specific label types. This distinguishes it from sibling tools like face_compare or OCR tools, which have different purposes.

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 mentions best-use cases (compliance scene checks, loan/insurance evidence review, anti-fraud triage), but does not provide exclusion criteria or contrast with alternatives. The sibling tools are sufficiently different that confusion is unlikely.

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 full behavioral disclosure. It enumerates return values ('risk level plus attack tag') and lists various attack types it covers (screen replay, print attack, synthetic face, etc.), giving good insight into tool behavior. However, it could be improved by mentioning file format/size limits or processing mode (sync/async).

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 two sentences, front-loading the core purpose in the first sentence and providing return values and use cases in the second. There is no extraneous information; every sentence adds value.

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 single parameter, no output schema, and the presence of sibling tools, the description covers the essential aspects: purpose, return values, attack types, and appropriate use cases. It is missing potential limitations like file size or format constraints, but overall it is reasonably complete.

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%, with the input schema already detailing the 'file' parameter's valid inputs. The tool description does not add significant new semantic information about the parameter, meeting the baseline expectation. No additional clarity needed.

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: detect if a face photo is genuine or spoofed/AI-forged. It specifies the resource (face photo) and action (detect liveness), and distinguishes itself from siblings like video_liveness_detect and face_compare.

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 usage contexts ('Best for lightweight anti-fraud before account opening, loan application, payment-risk step-up, or AI-agent human gate'), giving clear guidance on when to use it. It does not explicitly state when not to use it or mention alternatives, but the context is sufficient.

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 provided, so description carries full burden. It discloses what each page returns (main page fields, supplementary page fields), adding transparency beyond the schema. No contradictions.

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. Front-loaded with core purpose, immediately followed by output details and use cases. 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?

For a simple two-param OCR tool without output schema, the description adequately covers inputs (via schema) and outputs (per page). Missing aspects like error handling or image requirements, but overall sufficient given tool simplicity.

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%, baseline 3. Description adds value by explaining the effect of the 'side' parameter (main vs. supplementary page outputs), which is not fully captured in the schema's brief enum description.

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 extracts structured fields from a Chinese vehicle license, specifies fields per page, and lists use cases. It distinguishes from sibling OCR tools (id_card_ocr, driver_license_ocr) by targeting vehicle licenses.

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 use cases (auto loans, fleet onboarding, etc.), giving context for when to use. However, no direct comparison with sibling tools or exclusions for alternative tools.

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 provided, so description carries full burden. It mentions retry handling and file limits but does not disclose authorization needs, return value format, or side effects.

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 sentences with no wasted words. The purpose is front-loaded, followed by key behavioral info and limits.

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 covers purpose, use cases, retry, and limits. It does not describe the output format, but since there is no output schema, the description is reasonably complete for a detection 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 100%, so baseline is 3. The description adds useful constraints (max 20MB, recommended clip length) that are not in the schema, enhancing understanding.

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 detects whether a face video is genuine or an attack, with a specific verb and resource. It distinguishes from siblings like photo_liveness_detect by focusing on video.

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 example use cases (eKYC, onboarding) but lacks explicit guidance on when not to use or which sibling tool to choose instead (e.g., photo vs video).

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