document_intelligence_write_document

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

Annotations already carry the safety profile: destructiveHint=true, readOnly=false, and openWorldHint=true. The description adds useful routing context: execution goes through the platform's domain-agent dispatcher under the caller's JWT, tenant, and company scope. It does not, however, disclose the nature of the destructive behavior or what happens once the action runs.

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 description is compact, well-structured, and front-loaded with the core action. The args list is minimal and easy to scan, with no redundant 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?

A destructive write tool with no required parameters and generic free-text inputs needs more behavioral and input guidance than this. The output schema existing removes the need to explain return values, but the agent still lacks enough information about what `write_document` should be asked to do, what valid structured inputs look like, and what consequences the action may have.

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%, so the description carries the full burden for parameter meaning. It does add a little beyond the schema by framing `message` as a 'free-text objective' and `inputs` as an 'optional JSON string of structured inputs', but it provides no concrete example, expected input keys, or explanation of how the message maps to a write operation. This is insufficient compensation for the missing schema descriptions.

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 description states a verb ('Run') and a resource (the document_intelligence domain agent action `write_document`), so an agent knows this invokes that action. However, it never explains what writing a document actually does or how this differs from siblings like `document_intelligence_update_document` or `document_intelligence_create_report`. The purpose is clear at a mechanical-routing level but vague at a functional level.

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?

The description gives no guidance on when to use this tool versus alternatives. It does not mention prerequisites, whether it is preferred over `dispatch_domain_agent`, or what scenarios call for `write_document`. An agent must infer usage entirely from the name and context.

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