deep_research_chat

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

Annotations already disclose readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds authentication/scope context ('under your JWT, tenant, and company scope') and dispatcher routing, which is useful. It does not describe the actual side effects or state changes, but it also does not contradict the destructive hint.

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 short, front-loaded with the core action, and has a clean Args section. The routing sentence adds relevant scope information without excessive verbiage, though the Args bullets largely repeat schema property names.

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 an output schema present, return-value documentation is not required, and the two parameters are at least minimally explained. However, the description lacks any guidance on when deep_research_chat is the right tool relative to the many related deep_research/domain-agent siblings, and it does not explain expected behavior or consequences of invoking the chat action. This leaves a meaningful selection-and-invocation gap.

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 must compensate. It does clarify that message is a 'Free-text objective' and inputs is an 'Optional JSON string of structured inputs,' adding meaning beyond the bare string type. It still lacks concrete format details or examples for the structured inputs, so compensation is only partial.

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 uses a specific verb and resource: 'Run the deep_research domain agent action `chat`.' This tells the agent this is the chat action of the deep_research domain agent and distinguishes it from sibling actions like deep_research_synthesize and deep_research_research_query by name and action label. However, it does not explicitly differentiate itself from those siblings or explain what 'chat' behaviorally accomplishes.

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 provides no explicit guidance on when to use this tool versus alternatives such as deep_research_synthesize, deep_research_research_query, or dispatch_domain_agent. It only states the mechanism of routing through the domain-agent dispatcher, leaving the selection decision entirely to inference.

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