APICK OCR

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

Annotations already declare readOnlyHint=true, and the description adds helpful behavioral context: it returns full_text and mentions the cost of 8 points per call. No contradictions. It could mention error handling or rate limits, but for a read-only OCR tool this is adequate.

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 action in English, followed by a clarifying Korean sentence. It includes only essential information: purpose, use cases, output name, and cost. No wasted 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?

With one simple parameter and no output schema, the description sufficiently covers tool selection and expected output (full_text). It notes the general-purpose scope and cost. It could add return-format details or examples, but the current level is enough for an agent to invoke 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?

Schema description coverage is 100%, so the parameter image_url is already fully documented with format and size constraints. The description does not add extra meaning beyond naming 'image file' generically, so it matches 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 the action ('Extract text from an image file') and the resource (OCR), and explicitly scopes it to general-purpose images like document photos, scans, and screenshots. This distinguishes it from the sibling tools ocr_identi1-5, which presumably specialize in identity documents.

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 clear context on when to use this tool ('범용 이미지에 사용합니다' – for general-purpose images) and implies not for identity-specific OCR by contrast with siblings. However, it does not explicitly mention exclusions or name an alternative 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?

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds useful context about returning structured results and raw_text, and notes the point cost, but does not disclose error behavior or limitations beyond that.

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 brief, front-loaded with the core action, and includes only essential supplementary information (legal note, return format, point cost). No wasted sentences.

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 readOnlyHint and no output schema, the description covers the tool's purpose, return values, usage condition, and cost. It could be more complete by noting supported input constraints (already in schema) or failure scenarios, but overall it is sufficient.

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 covers 100% of parameters, so the image_url parameter is fully documented in the schema. The description adds no additional parameter-specific information beyond referencing the image.

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 identifies the exact resource ('Korean resident registration card (jumin card)') and lists key fields (name, resident registration number, address, issue date). This makes the tool's purpose clear and distinct from generic OCR tools, even though it doesn't explicitly compare to siblings.

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 usage for jumin card images but does not explicitly differentiate from sibling tools ocr_identi2-5. It provides a legal usage condition ('정보주체의 동의 등 적법한 처리 근거를 확보한 경우') but no guidance on when to prefer this tool over alternatives.

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 declare readOnlyHint=true, and the description adds that the tool returns structured results and raw_text without side effects. It also discloses a per-call cost ('[호출당 8포인트]') and a legal usage constraint, both beyond what annotations provide. No contradiction exists.

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 and front-loaded. The first sentence states the core purpose, the second adds output details, and the third provides legal and cost context. Each sentence adds value without unnecessary fluff, and the bilingual presentation is compact.

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 compensates by mentioning the return format ('구조화된 결과와 원문 텍스트(raw_text)') and example fields. It covers legal use, cost, and input requirements. It could list exact output fields or error behavior, but the tool is simple with one parameter, so the description is sufficiently 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?

The input schema already covers the single parameter (image_url) with 100% description coverage, including format and size constraints. The tool description adds no new parameter-level detail beyond stating that an image is processed, so a 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 a specific verb and resource: 'Extract key fields from a Korean driver license image via OCR.' It also distinguishes itself from sibling tools by explicitly mentioning Korean driver license and listing example fields, making its 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 clear usage context by requiring a legal basis ('정보주체의 동의 등 적법한 처리 근거를 확보한 경우에만 사용'), which is important for privacy-sensitive data. It does not explicitly contrast with sibling OCR tools, but the Korean driver license scope is implicitly 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 annotations already indicating read-only behavior, the description adds valuable context: it details the output format (structured fields plus raw_text), the specific fields extracted, and the per-call point cost. It also includes a compliance note about legal basis, which goes beyond annotation data.

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 efficient front-loading: the first sentence states the core purpose and output, the second adds compliance and cost information. There is no redundant or filler content.

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 tool with one parameter and no output schema, the description is sufficiently complete: it covers the input type, extracted fields, output format, and a legal caveat. More detail on error handling would improve it, but it is not essential for basic usage.

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 schema description covers 100% of the single parameter (image_url) with format and size constraints. The tool description does not add additional parameter semantics, so the baseline score 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 clearly states the tool extracts key fields from a passport image via OCR, listing specific fields like name, passport number, issue date, expiry date, and birth date. It also specifies that it returns structured results and raw_text, distinguishing it from generic OCR tools or sibling tools targeting 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 clear context: this tool is for passport images requiring OCR extraction. It also includes a usage restriction (only with legal basis such as consent), which serves as a when-not guidance. However, it does not explicitly compare to sibling tools or mention alternatives, 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 provide readOnlyHint=true, and the description aligns with that by describing an extraction (read) operation. The description adds context beyond annotations: it states that output includes structured results and raw_text, mentions a consent/legal basis requirement, and notes a cost of 8 points per call. This is valuable behavioral information not available from structured fields.

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 mostly concise and front-loaded with the action ('Extract key fields...'). However, it repeats the same information in both English and Korean, adding minor redundancy while still conveying important additional details (return format, consent, cost). It is efficiently written but not perfectly lean.

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 no output schema, so the description should clarify what the tool returns. It mentions 'structured results and raw_text' but does not specify which key fields are extracted, leaving ambiguity. The consent and cost details are useful, but the output spec is incomplete for a tool whose main value is extracting specific fields.

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 input schema already provides 100% coverage for the single parameter image_url, including allowed formats (image/png, image/jpeg) and maximum size (25MB). The description does not add additional parameter-level details, 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 tool extracts key fields from a Korean certified copy of resident registration (deungbon) via OCR. The verb 'extract' and the specific resource (deungbon image) clearly define its purpose and distinguish it from sibling OCR tools, which likely handle different 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 tool's scope is explicitly tied to a specific document type (deungbon), giving clear context for when to use it. It also adds a use condition: only when a legitimate processing basis (e.g., consent) is secured. However, it does not explicitly mention alternatives or when not to use this tool versus 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 declare readOnlyHint=true, and the description adds useful context beyond that: it specifies the return format (structured results and raw_text), the input type (photo of the card), the point cost (8 per call), and the legal requirement. 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 appropriately sized and front-loaded with purpose, followed by additional constraints. However, it contains redundancy, with the English sentence being repeated in Korean, which slightly reduces conciseness.

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 tool, the description covers purpose, parameter, return value, legal basis, and cost. It lacks explicit differentiation from sibling tools, but overall it is quite complete given the available annotations and schema.

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% with a detailed parameter description (HTTPS URL, image formats, max size). The description adds minimal extra meaning beyond the schema, so the baseline 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 tool extracts key fields from a Korean alien registration card via OCR, listing specific fields such as name, alien registration number, and issue date. This specific verb+resource distinguishes it from generic 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 a legal prerequisite (consent) but offers no guidance on when to use this tool versus sibling OCR tools like ocr_identi1-4 or the generic ocr. No alternatives or exclusions are mentioned, leaving the agent without clear selection criteria.

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