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

Goes well beyond the annotations (which only give readOnly/openWorld/idempotent/destructive hints) by disclosing auth requirement ('Requires an API key') and the billing model ('reserved up front and released for any file that fails'). These are consequential traits an agent would not learn from structured fields alone.

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?

Four tight sentences, each front-loaded with the highest-value fact first (the async submit action), then workflow, idempotency, billing, and auth. Zero filler.

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?

No output schema exists, but the description supplies the return value ('Returns a job_id') and the completion path via get_bulk_job, so an agent has everything needed to invoke and follow through 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 60%, and the description adds useful reinforcement of file_urls constraints (max 10, public https URLs) and idempotency_key retry semantics. However, it says nothing about callback_url, language_hint, or schema_version, leaving the two undocumented params unrecovered.

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 ('Submit'), resource ('SDS PDFs'), and scope ('up to 10... one asynchronous job'), which clearly distinguishes it from the sibling extract_sds (single) and get_bulk_job (polling). An agent can identify the tool's role without opening the 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?

Explicitly names the follow-up sibling ('poll get_bulk_job until status is completed or failed') and gives retry guidance ('Reuse the same idempotency_key when retrying'). The when-to-use and how-to-continue conditions are spelled out rather than inferred.

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