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

Annotations only cover the generic mutation profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true); the description adds far more: it spends credits, how billing works (per request or per page, configurable extras, project pricing, EUR 25 starting credit), that the result contains personal data, that the server never stores or logs it, and the 50-page/30-second timeout limits. This is exactly the behavioral context annotations cannot convey.

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 credit-spend warning, then the privacy warning, then the input contract, then the endpoint. Every sentence carries information, but the billing sentence is dense and somewhat sprawling with parenthetical commercial detail (Billing → Pricing, EUR 25 free credit) that could be tightened.

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?

For an 8-parameter mutation tool with no output schema and thin annotations, the description covers cost, privacy, input modes, and processing limits well, and names the extracted output fields so return content is inferable. It does not mention the asynchronous alternative (dochorizon_submit_async_capture) for documents that would exceed the synchronous limits, which is the one notable 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds a genuine cross-parameter constraint the schema does not encode (required count is 0, so nothing enforces it): the document must be given as exactly one of url, data_base64, or file_id. That exclusivity rule is real value beyond the 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?

States a specific verb and resource (extract a salary slip/payslip) and enumerates the extracted fields (employer, employee, period, gross/net pay, deductions), which clearly separates it from sibling capture tools for bank statements, identity documents, or e-invoices. An agent can select this over dochorizon_capture_generic or dochorizon_capture_financial without opening any schema.

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 invocation conditions: supply the document as exactly one of url, data_base64, or file_id, with size limits implied by each; configuration_slug is optional and dochorizon_list_configurations is named for finding one. It does not, however, state when to prefer an alternative such as dochorizon_submit_async_capture for large documents, so it stops short of explicit when-not guidance.

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