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

Annotations declare readOnlyHint=true and the description is consistent with that. It goes beyond annotations by specifying exactly what is masked, that the masked image is returned as base64 in the masked_image field, and the input constraints. 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 front-loaded with the core purpose and then packs in essential constraints: output field, single-document requirement, legal basis, and cost. The bilingual phrasing adds specificity rather than pure filler, and every clause carries information relevant to invoking the tool correctly.

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, the description is quite complete: it names accepted document types, input format, output field, and legal requirements. The main omission is that it does not enumerate which 'key fields' are extracted, which would be more relevant given there is no output 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?

The schema already covers image_url format and size with 100% coverage, so the baseline is 3. The description adds content-level constraints: the image must contain exactly one ID document, and lawful processing grounds are required. This is useful but does not deeply expand the parameter semantics.

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 names the exact resource types: Korean residence card, permanent resident card, and overseas Korean resident card. It also specifies the masking behavior of the last 6 digits, which clearly differentiates it from sibling tools like identity_document_driver_license, identity_document_id_card, and identity_document_passport.

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 clear invocation context: only one ID per image, PNG/JPEG images, and a lawful processing basis such as consent. It does not explicitly name sibling alternatives or state when not to use this tool, but the accepted document types are precise enough to guide selection.

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