document_intelligence_create_marketing_document

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

The routing/scoping note, 'Routes through the platform's domain-agent dispatcher under your JWT, tenant, and company scope', does add behavioral context beyond the annotations by disclosing the dispatch indirection and auth scope. However, given destructiveHint=true, the description does not explain what changes, gets overwritten, or what side effects to expect. The annotation already flags destructiveness, so the description adds some but not rich context.

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 and has a clear Args section, so it is not bloated. However, the first sentence is nearly tautological and does not earn its place; the whole description is roughly 50 words and spends its limited budget on mechanics rather than meaning.

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?

Despite having an output schema and a sibling list of hundreds of tools, the description never explains what the action produces, what 'marketing document' means in this domain, or how it differs from neighboring document_intelligence creation tools. An agent in a selection context lacks the information needed to invoke it correctly.

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, but it only provides thin glosses: 'Free-text objective' and 'Optional JSON string of structured inputs'. It offers no examples, no format expectations, and no explanation of how message and inputs interact. Both parameters are optional with defaults, which is unusual for a creation tool and left entirely unaddressed.

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 line, 'Run the document_intelligence domain agent action `create_marketing_document`', essentially restates the tool name in another format without explaining what creating a marketing document functionally entails. It adds the dispatcher-routing detail but never states the tool's purpose or output, so an agent cannot tell this apart from near-identical siblings like document_intelligence_create_marketing_collateral.

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?

There is no guidance on when to use this tool versus any of its many siblings (create_marketing_collateral, create_sales_collateral, create_report, dispatch_domain_agent). The line 'message: Free-text objective for the action' only implies usage without giving selection criteria, exclusions, or context about which objectives map to this action.

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