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

Adds context beyond the annotations: billing per document from prepaid credit, failures not billed, API key requirement, and the returned confidence_score/warnings. Annotations already cover openWorldHint and non-idempotency, so this extra operational detail is meaningful and consistent with them.

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 core action and output before secondary operational details. It is dense but every sentence carries information; no filler is present.

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 still sketches the return value (16-section record, confidence_score, warnings). Billing and auth are covered. Minor gaps remain around input size limits and processing time, but an agent has enough to invoke correctly.

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 all six parameters are already documented in the schema itself. The description only reinforces the file_url/file_base64 choice and adds no semantics for filename, language_hint, schema_version, or include_formats, so baseline 3 applies.

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 one Safety Data Sheet PDF') and describes the output shape (normalized 16-section record with confidence_score and warnings). The word 'one' implicitly separates it from submit_bulk_extraction, letting an agent pick the single-document tool without opening a 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 clear context for how to call it (file_url as public https URL or file_base64) and the cost model. It does not explicitly name submit_bulk_extraction as the alternative for batches, so routing guidance is implied by 'one' rather than stated.

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