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

Goes well beyond the annotations: it discloses that processing is asynchronous and this call polls until completion or times out at ~75 seconds, that files/results are not stored while upstream MinerU tasks persist up to 24h, and that billing is charged before the job is created with no automatic refunds. The coordinate-system caveat (content-list coordinates, not character-level, not rescaled to pixels) is exactly the kind of output nuance an agent could otherwise get wrong. Nothing contradicts readOnlyHint=false / openWorldHint=true / 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-loaded with purpose and return format, then constraints, then side effects, then licensing. Almost every sentence carries unique information; the MinerU license line is low-value for tool selection but short enough not to hurt.

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 one-parameter OCR call with no output schema, the description covers input constraints, return structure including the coordinate caveat and table_cell blocks, async/timeout behavior, retention, and cost. An agent has everything needed to invoke it correctly and predict the response.

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% with a single required 'files' array, so the baseline is 3. The description still adds real value by specifying per-file size limits, the allowed MIME set, the external-host restriction, and the DOCX exclusion — constraints the schema itself cannot express.

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 first sentence gives a specific verb and resource ('Extract text from images, screenshots, and scanned PDF pages') and the following sentence pins down the exact return shape (blocks with [x0,y0,x1,y1] boxes and page indexes). It does not explicitly contrast itself with siblings like extract_tables or convert_to_markdown, so differentiation is left implicit.

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 states hard input conditions (1-5 public https URLs, ≤20 MiB, supported formats, DOCX unsupported, private/local/metadata hosts rejected), which strongly implies when the tool is applicable. However, it never names an alternative tool for the excluded cases (e.g., local files, DOCX, table-only extraction), so an agent must infer routing from the sibling list.

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