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

The annotations only cover readOnly/destructive/idempotent hints, so the description adds crucial behavior: the tool enqueues an inference, polls up to ~30s, and returns a job_id if still running. It also discloses that it consumes Mindee API credits billed per page, which is not available in annotations. No contradiction with the annotations; readOnlyHint=false aligns with the enqueue/submit action.

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 compact: one sentence for the core action, one for input alternatives, one for async behavior, and one for cost/API details. Every sentence adds distinct information without redundancy.

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 tool with 10 parameters and no output schema, the description covers the submission flow, input modes, polling behavior, fallback job_id, cost implications, and API endpoint. It also names the sibling tools for polling and reading results, giving the agent a complete mental model of how to handle the response.

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%, but the description adds the critical constraint that document_url and file_base64 are mutually exclusive ('Provide EITHER document_url (a public URL) OR file_base64 (+ filename)'). It also clarifies that filename is for file_base64 uploads, complementing the schema's individual parameter descriptions.

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 opens with 'Submit a document (PDF or image) to a Mindee extraction model and return the structured fields,' clearly stating the verb and resource. It distinguishes itself from siblings by describing the enqueue/poll flow and referencing mindee_get_job and mindee_get_inference for follow-up, making its unique role among the listed tools unmistakable.

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?

It tells the agent to provide either document_url or file_base64, and explains that if processing isn't complete it returns a job_id to poll with mindee_get_job then read with mindee_get_inference. This gives explicit when-to-use guidance and names the alternative tools for subsequent steps. It also notes the paid API credits, which is a practical consideration for deciding to invoke.

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