document_intelligence_chat

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description does not contradict them. It adds minor context by saying routing happens through the domain-agent dispatcher under JWT/tenant/company scope, but it discloses no concrete side effects, return behavior, or cautions, leaving the destructive implication unexplained.

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 brief and front-loaded with the core action, followed by a compact args section. It wastes no words, though a single sentence describing the effect of the chat action would make it more informative without much added length.

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?

With no required parameters and an output schema present, the description is minimally viable: parameter semantics and scope routing are covered. Yet for a destructive-flagged generic agent chat inside a very large sibling set, it lacks a statement of what document intelligence chat can do, what it may change, or when it should be preferred.

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%, and the description compensates by defining `message` as 'Free-text objective' and `inputs` as 'Optional JSON string of structured inputs.' This is meaningful, though it remains vague about what structured inputs should look like and how they modify the action.

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 first line names the exact operation: running the `chat` action of the document_intelligence domain agent, and adds dispatcher/scope context. However, it never explains what the chat action actually accomplishes or how it differs from sibling document_intelligence_* and other domain chat tools, so it stops short of full differentiation.

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?

No guidance is given on when to use this generic chat versus the many sibling actions such as document_intelligence_search_documents, ask_document_agent, or dispatch_domain_agent. The dispatcher/scope note is mechanical context, not selection guidance.

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