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

Annotations already cover safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false), yet the description still adds real value: experimental status, bounded retries, 'retain idempotency_key', output shape (JSON/CSV with source quotes, null for missing data), and a candid limitation that schema/source matching is checked but semantic correctness is not guaranteed. Only the failure/timeout behavior and what happens after retries are exhausted remain unstated.

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?

Six short sentences, each carrying distinct information, with the prerequisite check and the scope limits front-loaded. The telegraphic fragments ('No URL fetching or OCR.' 'Poll get_studio_job.') read tersely but are efficient rather than wasteful.

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 an asynchronous one-shot submission with nested parameters, no output schema and no schema descriptions, the definition supplies the essential lifecycle (availability check, submit, poll get_studio_job), idempotency handling, and output expectations. The gaps are the unexplained 'consent' requirement and access_token/auth handling, which matter for a tool with a mandatory consent gate.

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 0%, so the description must carry parameter meaning, and it only partly does: it conveys the 1-6 record bound, that records are text rather than URLs, nonconfidentiality, and that idempotency_key should be retained. It says nothing about the mandatory 'consent' flag (const true), the optional access_token, or the 2000-character text limit, leaving several required inputs semantically unexplained.

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 names a specific verb and resource: 'structured extraction from one to six nonconfidential product records supplied as text', plus explicit exclusions ('No URL fetching or OCR') and a scope bound (1-6 records). It distinguishes itself from the generic job-submission siblings (submit_compute_job, submit_chat_job, submit_image_job) by naming the task type, though it never explicitly contrasts itself with them.

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 gives a concrete prerequisite ('Check catalog_extraction.available first') and a concrete follow-up ('Poll get_studio_job'), and the 'No URL fetching or OCR' line implicitly states when this tool is not appropriate. It stops short of naming an alternative tool for URL/OCR cases or stating what to do if availability is false.

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