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

Adds substantial context beyond the annotations: it leads with SPENDS CREDITS, explains per-request/per-page billing (with extra-component cost), cites the project pricing location and EUR 25 free credit, notes the result may contain personal data, and warns that >50-page documents time out. These cost, privacy, and limit disclosures are exactly what mutations need and are not in the annotation set.

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?

Front-loads the cost warning, then purpose, output, privacy, billing, and input method in a logical order with no filler sentences. It is dense and slightly long, and the trailing endpoint path is marginal for an agent, but each clause carries information.

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?

With no output schema, the description routes the agent to dochorizon_get_prompt_schema for the return shape, and covers cost, input modes, password handling, and timeouts. It stops short of describing the return envelope itself, but the sibling reference largely compensates for the missing output schema.

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 schema documents each parameter, but the description still adds the crucial mutual-exclusivity rule (exactly one of url, data_base64, file_id) and characterizes each option (public https, small files, stored file), which the schema 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?

States a specific verb and resource: extract data from a document using a Prompt Builder configuration, explicitly defined as an LLM extraction prompt the user created. This clearly differentiates it from the fixed-schema siblings like capture_bank_statement or capture_einvoice, which extract to predefined formats.

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?

Gives concrete usage constraints: supply the document as exactly one of url, data_base64, or file_id, and points to dochorizon_get_prompt_schema and dochorizon_list_prompt_configurations for setup. It does not explicitly state when to prefer this over the generic or domain-specific capture siblings, leaving that routing to inference.

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