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

With no annotations, the description carries full behavioral disclosure. It explains the routing logic (Japanese to manga-ocr, other languages to their OCR packs, low-confidence escalation to a vision model) and the exact return contents (text blocks in reading order, detected language, engine, vertical flag). This goes well beyond what the input schema provides.

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 dense but organized: purpose first, then routing behavior, output contents, input format, and language guidance. Each sentence contributes necessary information without redundancy, and the most important distinction is front-loaded.

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?

Even without an output schema, the description explains return values in sufficient detail: text blocks in reading order, detected language, OCR engine, and vertical-page flag. It also covers input encoding and language selection. The api_key auto-provisioning is documented in the schema, so the description remains complete enough for correct invocation.

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%, so the baseline is 3. The description adds meaningful parameter guidance beyond the schema: passing lang explicitly yields the best non-Japanese result, while default 'auto' detects language. This is practical, behavior-relevant information that the schema's generic 'Language hint' does not convey.

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's purpose: OCR a comic/manga page, with a language-aware routing distinction that sets it apart from a generic 'manga means Japanese' assumption. It is specific about the resource and behavior, though it does not explicitly name sibling tools like ocr_image for differentiation.

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: provide the page as base64, pass lang explicitly for non-Japanese content, and rely on auto-detection otherwise. It does not explicitly state when to prefer this tool over siblings or when not to use it, but the intended use case is strongly implied.

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