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

Annotations already declare destructiveHint=true, but the description goes further: it explains the full out-of-band workflow (returns upload_url, PUT writes the document), the permission lifetime (2 hours) and its scope (single document), and that the curl response itself carries the summary (bytes, blocks, tables, headings, sha256). This is behavioral context the annotations cannot provide.

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 the key differentiator, then the workflow, then the mode branch. Slightly long with a mixed prose/command layout, but each section (return value, curl usage, mode semantics, permission scope) carries distinct information rather than repetition.

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, yet the description describes the return (upload_url) and the payload returned by the subsequent PUT, so an agent needs nothing else. The permission expiry and scoping are also covered, making this fully self-contained for a two-step upload flow.

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 real meaning: it explains the document_id vs name interaction as an either/or mode switch, and that base_version is optional exactly as in update_document. It leaves workspace_id and parent_document_id to the schema, which is reasonable.

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 (escribir/subir) and resource (documento) and immediately distinguishes the mechanism: the content never passes through the model, unlike create_document/update_document. The reader knows exactly what this tool does and why it exists alongside its siblings.

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 states the selection condition (fast path for content >~20 KB or already in a file) and disambiguates the two modes: document_id replaces an existing document, name-without-document_id creates a new one. It even cross-references update_document for the concurrency semantics.

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