Analyze image (vision VLM)

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

Annotations are absent, so the description carries full weight. It reveals defaults (mode=conformance, vlm=primary), the meaning of nsfw and fallback slots, and the meaning of free mode. It does not disclose side effects or failure modes, but this is a read-only analysis tool, so risks are limited.

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 purpose, followed by parameter clarifications in a consistent structure. The parenthetical-heavy style is information-dense but slightly dense with specification text; still every sentence adds value.

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?

Given the simple schema (flat, 6 params, 2 required) and no output schema, the description covers the main aspects: purpose, defaults, parameter semantics. It lacks explicit return-value behavior or error conditions, but for an analysis tool this is a minor gap.

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?

All parameters are described in Japanese with meaningful detail: source format, prompt content guidance, enum semantics for mode and vlm, max_tokens bounds and default, max_long_edge meaning including the 0=unlimited case and env inheritance. This goes well beyond the JSON schema.

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?

Description states an exact verb ('解析する'), a specific resource ('画像'), and its main use case ('生成仕様への準拠検査'). It also distinguishes from sibling compare_images by focusing on single-image analysis against a prompt/spec rather than comparison.

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?

Description explains when to use the default conformance mode and what to include in the prompt for conformance checks, plus VLM slot selection semantics. It does not explicitly contrast with the sibling compare_images, but the single-image vs comparison distinction is implicit.

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