ai_ocr

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

With no annotations provided, the description must carry full behavioral disclosure. It mentions the cost and the L402 payment mode, giving some insight into payment requirements. However, it does not disclose side effects, error behavior (e.g., invalid URL), or whether the tool is read-only.

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 very concise with one sentence plus a cost hint. It is front-loaded and efficient, though it could benefit from a bit more structure (e.g., separate sections) for clarity. Still, it is appropriately sized for the tool's simplicity.

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 no annotations or output schema, the description should cover behavior, usage, and return format. It addresses cost and L402 mode but omits details about return values (presumably extracted text), error conditions, and limitations. The description is somewhat incomplete for an agent to fully understand the tool's capabilities without assumed knowledge.

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 has 3 parameters with 67% coverage (preimage and macaroon have descriptions in the schema). The tool description adds no additional parameter semantics beyond what is already in the schema. The required 'image_url' parameter lacks a description both in schema and description, leaving its format or constraints unclear.

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 'Extract all visible text from an image URL,' which is a specific verb+resource combination. It distinguishes the tool from siblings like ai_vision (image analysis) and ai_extract (general extraction) by specifying OCR functionality.

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 includes a cost hint '[25 sats per call]' which implies usage context but does not explicitly state when to use this tool over alternatives or provide guidance on when not to use it. No comparison with sibling tools is given.

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