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

Annotations already declare readOnlyHint=true, so the description doesn't need to state non-mutating behavior. The description adds a practical detail — the per-call cost of 10 points — and mentions use cases, which is helpful context beyond the annotations. It does not describe the nature of the similarity score (e.g., range, interpretation), but this is not a conflict. Given annotations cover the safety profile and the description adds a bit of operational context, a 3 is fair.

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 — three short sentences plus a cost note in brackets. The primary action and purpose are front-loaded, and every sentence adds value: what it does, use cases, and cost. There is no filler or redundancy.

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 two-parameter tool with no output schema, the description is mostly complete: it states inputs, outputs (a score), and use cases. The significant gap is the lack of any indication about the score's format or scale (e.g., 0–1, percentage), which an agent would need to interpret results correctly. Since the description carries the responsibility for explaining return values when no output schema exists, this omission makes it incomplete enough for a 3.

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 (image_url, compare_image_url) are fully described with format restrictions and size limits. The description does not add semantic meaning beyond the schema; it merely restates roles (base vs. comparison) that are already evident from parameter names and the schema descriptions. With full schema coverage, 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 clearly states the verb 'Compare' with two distinct resources (base image and comparison image) and the outcome (similarity score). It further specifies use cases (origin verification, duplicate detection), which distinguishes it from all sibling tools that handle video, face, NSFW, audio, and text — none relate to image similarity. This is a specific and unambiguous definition.

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 provides clear usage context by listing typical scenarios ('원본 검증, 중복 이미지 탐지 등' – origin verification, duplicate detection), which guides an agent on when to invoke it. However, it does not explicitly state when NOT to use it or mention alternative tools, though no sibling tool is directly comparable. Since context is given but exclusions are absent, a 4 is appropriate.

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