document_intelligence_create_spreadsheet

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

Annotations already signal destructiveHint=true and idempotentHint=false. The description adds some useful operational context by stating that the call routes through the domain-agent dispatcher under JWT, tenant, and company scope, which clarifies authentication and authorization boundaries. It does not, however, explain what side effects creating a spreadsheet may have, whether existing files can be overwritten, or what the domain agent will do with the objective.

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 front-loaded, starting with the action name and then briefly explaining routing and arguments. It includes only necessary sections and does not waste tokens, though the routing sentence could arguably be merged into the first sentence.

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 domain-agent wrapper with an open-world hint, destructive hint, and a free-text objective parameter, this description is too thin. It does not tell an agent what the create_spreadsheet action is for, what inputs the agent should provide, what the generated artifact will be, or when to choose this over the plain `create_spreadsheet` sibling. The output schema exists, but the missing behavioral and selection context makes the tool hard to invoke confidently.

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 compensate for the schema's bare string-typed parameters. It does provide basic semantics: `message` is a free-text objective and `inputs` is an optional JSON string of structured inputs. This is helpful but shallow; it gives no guidance on what kind of structured inputs are expected, what format the JSON should follow, or what a well-formed objective looks like.

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 says it runs the `create_spreadsheet` domain-agent action, which names the verb and resource clearly. However, it does not explain what the action actually does, what kind of spreadsheet is created, or how it differs from the many document_intelligence siblings such as `create_report`, `create_slide_deck`, or `create_spreadsheet` in the sibling list. It is functional but leans heavily on the tool name rather than adding real purpose detail.

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 when-to-use guidance, no exclusions, and no comparison to alternatives like `create_spreadsheet` or `document_intelligence_create_report`. The only usage signal is 'Run the document_intelligence domain agent action', which implies delegation but never tells an agent when this wrapper should be selected over other document-creation tools.

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