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

Goes well beyond the annotations by disclosing the credit-billing model (per request or per page, extra configurable components add cost, project pricing location, EUR 25 starting credit) and the critical fact that nothing is sent to a network. This is exactly the cost/authorization context an agent cannot get from the structured fields.

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 most decision-relevant fact ('SPENDS CREDITS') and keeps to a single tight paragraph. The free-credit detail borders on marketing, but overall most sentences carry operational weight.

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 compensates by describing the returned structure, and it covers input alternatives, billing, network behavior, and page/timeout limits. Nothing needed to call it correctly is missing.

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, but the description adds the mutual-exclusivity constraint ('exactly one of url, data_base64 or file_id') and sizing preference ('prefer url or file_id for anything bigger') that the flat properties object does not express.

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 ('read an invoice with the financial model') and names the exact output contract ('Universal Invoice structure used for e-invoicing ... parties, lines, tax subtotals, totals, payment means'). This meaningfully separates it from capture_generic and capture_financial, though it never explicitly routes the agent between the many capture_* siblings.

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 implies its context (invoice capture for e-invoicing) and gives input-format selection guidance ('give the document as exactly one of url, data_base64 or file_id'). However it never states when to pick this tool over dochorizon_capture_financial, capture_generic, or convert_einvoice, so alternative selection is left to inference.

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