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

Annotations already declare destructive=true, idempotent=true, and openWorld=true, so the safety profile is partly covered. The description adds genuine non-annotation context: it does not publish, replacement preserves existing publication and access controls, and only a 'ready' state confirms the save. What actually gets destroyed on replacement remains 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?

Four short, front-loaded sentences with no padding, and the key non-publishing constraint appears early. However, fragments like 'Only ready confirms saved state' are terse to the point of ambiguity rather than clear.

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 destructive, open-world mutation with no output schema, the description covers the non-publishing and replacement-preservation behaviors but leaves the required jobId, the meaning of the 'ready' state, and the returned result unaddressed. Adequate but with visible gaps.

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 description coverage is 0% across two parameters, so the description must compensate. It implicitly maps to fetchUrl via 'explicitly fetch the original direct HTTPS source' versus 'uploaded bytes', but jobId (the required uuid) is never explained, leaving half the parameters uninterpreted.

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 concrete action (inspect uploaded bytes and save the private imported document) plus an alternate path (fetch the original direct HTTPS source), which is specific enough to distinguish it from begin_document_import or get_document_import_status. The 'Does not publish' clause further separates it from publish_document, though the phrasing is dense.

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?

Usage is implied (this is the completion step of the import flow, and 'Does not publish' implies a boundary) but no sibling tool is named and there is no explicit when/when-not guidance relative to get_document_import_status or cancel_document_import. An agent must infer the sequencing.

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