APICK OCR

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

Annotations already mark it as read-only, but the description adds useful non-obvious behavior: it returns the complete extracted text as 'full_text' and discloses the per-call cost of 12 points. This goes beyond the structured annotations, though it does not discuss error cases or what happens with unsupported input.

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 core action, followed by usage context and cost. There is slight redundancy between the English sentence 'Extract text from an image file (OCR)' and the Korean sentence that repeats the same idea, which prevents a perfect conciseness score.

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, read-only OCR tool with no output schema, the description covers what an agent needs: the action, the return shape (full_text), the intended image types, and the cost. The input parameter constraints are fully handled by the schema, so no critical information 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?

The only parameter, image_url, is already fully documented in the input schema with details about HTTPS URL, allowed MIME types, and the 50MB size limit. The description adds no additional parameter-level meaning, so the baseline score of 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 uses a specific verb and resource: 'Extract text from an image file (OCR)' and further clarifies it returns 'full_text'. It also positions itself for '범용 이미지' (general-purpose images) such as document photos, scans, and screenshots, which implicitly separates it from sibling OCR tools like ocr_identi* and identity_document_*. This makes the tool's purpose unmistakable.

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 says to use it for '문서 사진, 스캔 이미지, 캡처 화면 등 범용 이미지', giving clear context for when this tool is appropriate. However, it does not explicitly state when not to use it or point to alternatives like the identity-document OCR siblings, so it falls short of a 5.

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 mark the tool as readOnly and not open-world, and the description adds useful behavioral context: it returns structured fields plus raw_text, mentions the per-call point cost, and warns about legal compliance. There is no contradiction with 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 short and front-loaded with the core purpose. The English and Korean sentences partly duplicate each other, but the additional legal and cost information is valuable and does not create meaningful 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?

With one parameter, a complete schema, and readOnly annotations, the description covers the input, extracted fields, output format, legal condition, and cost. It lacks explicit error/edge-case behavior and sibling differentiation, but it is sufficient for a simple OCR 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?

The only parameter, image_url, is fully documented in the schema with format and size constraints, so the schema carries the parameter semantics. The description adds little beyond restating that the image is a resident registration card photo, which is already implied by the tool's purpose.

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 action and resource: extracting key fields from a Korean resident registration card image via OCR, and it lists the fields extracted. It is clear, but it does not distinguish this tool from sibling tools like ocr_identi2–5 or identity_document_id_card.

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 legal precondition: use only when a lawful basis such as data subject consent has been secured. However, it does not explain when to choose this tool over the many alternative OCR/ID document tools, leaving variant selection to inference.

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 the description adds useful behavioral details beyond that: it returns structured results plus raw_text, extracts specific fields, and notes the cost per call. It does not mention failure modes or edge cases, but for a read-only OCR tool the added context is meaningful.

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 short and front-loaded with the core purpose. The English/Korean duplication creates minor redundancy, but the legal-consent caveat and point cost are each valuable enough to justify their inclusion.

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 single-parameter tool with no output schema, the description adequately covers expected outputs (structured result and raw_text) and examples of extracted fields. It could be more complete by distinguishing among the many sibling OCR tools, but nothing essential to invoking this tool correctly 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% for the single image_url parameter, including allowed formats and max size, so the schema already fully documents the parameter. The description adds no additional parameter-level guidance, matching the baseline of 3.

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 a specific verb ('Extract') and resource ('Korean driver license image via OCR'), and lists example fields (name, license number, birthdate). It does not explicitly distinguish this tool from siblings like ocr_identi1/3/4/5 or identity_document_driver_license, so it stops short of a 5.

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 usage condition: use only when a legitimate processing basis such as data subject consent is secured. This acts as a when-not restriction and adds compliance context, though it does not explicitly compare against alternative OCR or identity-document 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?

Annotations already declare readOnlyHint=true, and the description adds useful context: it returns both structured fields and raw_text, requires a legal basis due to sensitive personal data, and notes a per-call point cost. 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 compact and front-loaded with the main purpose. The English and Korean sentences are somewhat redundant, but the Korean sentence adds field names and raw_text detail, and the legal/cost notes earn their 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?

There is no output schema, so the description compensates by naming the expected outputs: structured fields such as name, passport number, issue/expiry dates, birth date, plus raw_text. It could be more precise about exact output keys or failure behavior, but it is adequate for a one-parameter OCR 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 for the single parameter image_url is 100%, with the schema already specifying HTTPS, allowed MIME types, and the 50MB limit. The description adds nothing beyond referring to a passport image, so the baseline score of 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 action: extract key fields from a passport image via OCR, and lists examples of extracted fields. It does not explicitly differentiate itself from closely named siblings like identity_document_passport or ocr_identi1/2/4/5, so it stops short of a 5.

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 an important condition for use: only when a legal processing basis like consent has been secured. However, it provides no guidance on when to choose this tool over the many sibling passport/OCR tools, leaving tool selection largely implied.

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 mark it read-only (readOnlyHint=true), so the description only needs to add context. It adds that output includes both structured results and raw_text, discloses the 12-point cost, and warns about legal processing grounds. 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 core is front-loaded and the legal/cost notes are valuable, but the English and Korean sentences are largely redundant and could be merged without losing meaning.

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, so the description carries the burden of explaining output. It mentions 'structured results and raw_text' but does not say which fields are extracted or in what structure, leaving an agent to discover this only by calling 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 100% and already specifies image_url format (https, png/jpeg, max 50MB). The description adds nothing about the parameter beyond saying it is an image of the deungbon, 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?

The description names a specific verb ('Extract key fields'), a specific resource ('Korean certified copy of resident registration (deungbon) image'), and the OCR method, which distinguishes it from sibling OCR/identity tools by document type. The Korean sentence reinforces the exact subject matter.

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?

It gives a clear usage context (deungbon OCR) and a legal prerequisite ('only use with legal basis/consent'), but it never tells the agent when not to use this tool or points to alternatives among ocr_identi1-5/identity_document_* 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 already mark the tool read-only, and the description adds useful behavior beyond that: it returns structured fields plus raw_text, and it discloses a per-call point cost. No contradiction exists. It does not cover error behavior or image failures, but the additional context is meaningful.

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: an English summary, a Korean sentence that adds fields/output/legal condition/cost, and no filler. It is front-loaded with the action and resource, and every clause contributes information.

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 one-parameter OCR tool with annotations, the description is nearly complete: it names inputs, example fields, output types, legal precondition, and cost. With no output schema, the raw_text/structured-result mention helps, though a fuller field list would make it 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 coverage is 100% and the only parameter image_url is fully described with URL type, allowed MIME types, and size limit. The description adds no new parameter semantics and is not required to, so the baseline of 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 uses a specific verb ('extract') and resource ('Korean alien registration card image') and names example fields, clearly identifying the tool's function. It does not explicitly differentiate from sibling OCR/identity tools like ocr_identi1-4 or identity_document_residence_card, so it stops short of a 5.

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 states the clear context: use when a Korean ARC image needs key-field extraction via OCR. It also gives a concrete prerequisite (secure legal basis/consent before processing). It does not spell out when-not-to-use or name alternatives, which would have made the guidance stronger.

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