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

Annotations already flag non-readonly, open-world, non-idempotent, non-destructive behavior. The description adds meaningful context beyond annotations: paid per-page credit consumption, enqueue-and-poll behavior with a ~30s window, and job_id handoff to sibling tools. It does not explain whether duplicate submissions create duplicate billable inferences, which would be useful given idempotentHint=false.

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 core action and return value, then gives input mode, async behavior, cost warning, and endpoint in compact sequence. Every sentence contributes operational detail; the endpoint reference is technical but relevant for an API-integrated agent.

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 10-parameter extraction submission with no output schema, the description covers return shape at a high level, async completion behavior, polling alternatives, input source options, and cost implications. Nothing essential for correct invocation appears 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 description coverage is 100%, so the baseline is 3; the description still adds value by centralizing the critical mutual exclusivity of document_url and file_base64 and pairing file_base64 with filename. It does not cover optional flags like rag, polygon, confidence, raw_text, or alias, but those are clearly documented in 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/resource combination: submit a PDF/image to a Mindee extraction model and return structured fields. It also distinguishes the async handoff path from the sibling tools (mindee_get_job, mindee_get_inference), so an agent can separate this from polling/read tools.

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?

Explicitly states the alternative input modes (document_url OR file_base64 + filename) and the async escalation path when processing exceeds ~30s. It also warns that calls consume paid credits, giving clear when-to-use context and a cost-related caution.

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