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

Annotations only declare the safety profile (readOnlyHint=false, openWorldHint=true, non-idempotent, non-destructive); the description adds the operationally important traits: asynchronous execution that polls until done or times out near 75 seconds, per-table merged-cell expansion semantics, accuracy caveats for borderless/handwritten tables, no retention of uploads or results, ≤24h upstream retention, and a billing charge placed before the job is created with no refunds.

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 capability and output shape are front-loaded, then constraints, then behavior, then billing – a sensible order. The trailing 'Powered by MinerU' and license-URL lines are attribution rather than agent-relevant guidance, a small amount of non-earning text.

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 only one parameter and no output schema, the description carries the burden well: it names the returned fields (row_count, column_count, page_idx, bbox), discloses async/timeout behavior, states accuracy limits, and covers storage and cost implications. An agent has enough to call it correctly and to set expectations on the result.

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%, so the baseline is 3, but the description adds call-critical constraints absent from the schema: the 20 MiB per-file cap, the accepted file extensions, and the rejection of private/local/metadata hosts. It adds real meaning on top of 'array of https URIs' rather than restating it.

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 tables from PDFs and images') and specifies the exact output shape (HTML plus a row/column matrix), which lets an agent distinguish it from ocr_image or convert_to_markdown by result type. It never names those siblings explicitly, so routing still requires the agent to infer.

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 concrete applicability constraints: 1-5 public https URLs, ≤20 MiB each, a supported format whitelist, rejection of private/local/metadata hosts, and an explicit negative case (DOCX is not supported). It stops short of saying when to prefer a sibling such as convert_to_markdown or ocr_image instead.

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