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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is partly covered. The description adds real behavioral context beyond them: replacement needs the current revision as expectedRevisionId (optimistic concurrency), reader URL/access settings are preserved, a reserved job is not yet completed, and URL fetching is deferred to complete_document_import. Return format and failure modes 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?

Front-loaded with the core action and supported formats, then constraints, then the replacement and two-phase-job caveats. Every sentence carries distinct information with no filler.

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 7-parameter, nested-schema mutation with no output schema, it conveys the workflow shape well (reserve now, complete later) and the replacement contract. It is not fully complete: several parameters (htmlMode, workspaceId, idempotencyKey) are undocumented, though status/return info is delegated to sibling tools.

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 0%, so the description must carry parameter meaning, and it only partly does: it explains the replace path (documentId plus current fileRevisionId as expectedRevisionId) and implies source.kind='url'. It says nothing about htmlMode's static/interactive enum, workspaceId, idempotencyKey, title, or declaredBytes, leaving several params undocumented.

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 ('Import an existing PDF, image, HTML file or direct HTTPS URL as a private document') and immediately bounds scope by naming unsupported types (Office, video). This clearly separates it from siblings like create_document and complete_document_import without opening a schema.

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 when/when-not guidance: file bytes must originate from the authenticated embedded chooser or supported attachment transfer, never a local path, and Office/video are unsupported. It also routes the URL-fetch follow-up to complete_document_import. It stops short of explicitly contrasting against the nearest sibling (create_document) or stating prerequisites like permissions.

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