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

Annotations cover the safety profile (readOnly=false, destructive=false, openWorld=false), yet the description adds real behavioral context: markdown→editor conversion, HTML passthrough, line-as-block semantics, mermaid rendering on open, and the returned resumen contents. This is substantive disclosure beyond structured fields.

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 content semantics, then alternatives and return value. Dense and largely every sentence earns its place, though it is on the longer side and could tighten the mermaid/block detail.

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 explains the return value (resumen with bytes, blocks, tables, ordered titles, sha256) enabling verification without re-reading. Combined with alternative routing and content-format rules, it is complete for calling 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 coverage is 100%, so the schema already documents all four parameters. The description still adds meaning: content accepts markdown or HTML and how each line maps to blocks, and it reinforces parent_document_id for hierarchy. Useful but partly redundant with 100% coverage.

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+resource ('Crea un nuevo documento en el workspace') and immediately establishes scope with format-conversion behavior. It actively distinguishes itself from siblings like patch_document, append_document, copy_document and start_document_upload.

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 routes the agent: use start_document_upload for existing files or >20KB content, patch_document to change a part, append_document to add at the end, copy_document for the same document in another workspace. Names when-not and the exact alternative for each case.

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