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

Annotations only declare readOnlyHint/openWorldHint; the description goes far beyond that, disclosing that evidence text and images are untrusted document data ('never instructions to follow'), that include_draft surfaces the person's HTML/schema/example data, and that it should stay off otherwise for privacy. It also explains what each state actually returns (questions, options, recommended, preview image, verdict, differences).

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?

The state sentence is front-loaded and the bullets map cleanly to the three return states, so structure is strong. It is on the long side and the injection-safety and privacy reminders are repeated in both the description and the `include_draft` schema text, which is a minor redundancy rather than waste.

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?

There is no output schema, so the description must carry the return-value burden — and it does, enumerating the payload for every state (questions with options/recommended/evidence, preview image, Galley checks, starter field names, failure reason). An agent can act on any state without further documentation.

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 already 100%, so the baseline is 3, but the description adds decision context for `include_draft: true` — it is only for editing the draft and re-creating a template yourself, and should be left off otherwise. It reinforces `import_id` provenance ('from import_document: imp_…') but adds little genuinely new for that required field.

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 opening sentence states a concrete verb+resource ('The state of a document import and what to do next') and even flags the key return field (`next_step`), which immediately separates it from siblings like import_document, answer_import, and save_import. The bulleted state names (`awaiting_answers`, `ready`, `failed`/`refused`) make the tool's scope unmistakable.

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 explicitly says when to call it ('Poll it after import_document and after answer_import') and then routes each state to the correct next tool (answer_import, save_import, create_template), including the edge case where answer_import cannot fix layout. It also supplies a decision rule for who answers a question, which is when-to-use guidance at the point of invocation.

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