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

Goes well beyond the annotations by disclosing credit spend and the billing model (per request or per page, project pricing, EUR 25 free starting credit), that no webhook or human review exists, that identity/salary_slip/bank_statement results contain personal data, and the concurrency exemption. These are exactly the traits an agent cannot infer from readOnlyHint/openWorldHint/idempotentHint.

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-loaded with the cost warning in caps and otherwise dense with only relevant content; every clause carries information (billing, privacy, polling chain, input modes). It is a single packed paragraph with nested parentheticals, which makes it slightly heavy to scan but not padded.

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 a 9-parameter, high-complexity, no-output-schema tool, it covers everything needed: return value (job_id), follow-up chain, cost, personal-data implications, input-mode exclusivity, and a pointer to dochorizon_list_configurations for configuration_slug. Nothing required 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 real meaning the schema does not state: 'exactly one of url (public https), data_base64 (small files) or file_id (a stored file)', an explicit mutual-exclusion rule for the three input modes. It also ties configuration_slug to added cost, which the schema does not.

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+resource+effect: 'queue one document for capturing and return a job_id right away'. It also names the downstream siblings (dochorizon_get_async_job, dochorizon_get_async_job_result) and distinguishes itself from the synchronous capture_* family by scoping itself to long documents and bursts.

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 a clear usage condition ('Use it for long documents and bursts… async jobs are not subject to the concurrent-request limit') and defines the correct call sequence (submit → poll → read result). It lacks an explicit when-NOT-to-use statement pointing back to the synchronous capture_* tools for small single documents, so it falls short of full routing guidance.

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