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

Annotations already declare readOnlyHint=true, so the tool is known to be non-mutating. The description adds value by specifying the cost (20 points per call), the legal requirement, and the fact that it returns a masked image. It does not contradict annotations, and it gives context not present in the schema, such as the legal basis constraint.

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 (one bilingual) and effectively packs the core function, parameters, legal requirement, and cost into a compact block. It is front-loaded with the main verb and outcome, followed by the type details and usage caveat. While it repeats some schema information, it does so succinctly and without 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 tool with only two parameters and no output schema, the description covers the essential context: what it does, what the inputs mean, the legal prerequisite, and the cost. It does not describe the output format in detail, but it states it returns the masked image, which is sufficient. Given the schema handles input constraints (URL format, size), the description is complete enough for an agent to call 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?

Schema coverage is 100% (both parameters have descriptions), so the baseline is 3. The description adds meaning by elaborating each type value (e.g., type 3 is 'mask except first digit of last part') and clarifies that both inputs are mandatory. This goes beyond the schema's terse '가림 처리 타입' and provides concrete interpretation for the agent.

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 states a specific verb ('mask'), a clear resource ('resident registration numbers found in an image'), and the outcome ('return the masked image'). It explicitly enumerates four masking types, and the tool is clearly distinct from sibling tools that focus on identity-document recognition or authentication. There is no ambiguity about the tool's function.

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 clearly states that both the image and the type parameter are required, and it lists the four allowed type values. It also provides a critical usage condition: only use with a legitimate processing basis such as data-subject consent. It does not explicitly contrast with alternatives, but the sibling tools are obviously different in purpose, so this is adequate.

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