crm_chat

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=true), so the description need not repeat it. The description adds useful context by stating the action executes under JWT, tenant, and company scope, which implies auth-bound behavior. It does not contradict any annotation, and there is no contradiction between the described 'run action' semantics and the destructiveHint flag, though the description could note that the action may have real-world side effects.

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 tight: a one-line purpose, a single routing sentence, and a two-item Args list. It is front-loaded with the core action and every sentence earns its place. Minor deduction because the Args block could arguably live in the schema, but overall this is efficient and well-ordered writing.

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 two-parameter tool with an output schema, the description covers purpose, routing scope, and both parameters, which is close to adequate. The gap is that destructiveHint=true and openWorldHint=true suggest the chat action can mutate CRM state or external systems, yet the description never hints at what kinds of objectives are safe versus consequential, making it incomplete for an agent deciding how to phrase a request.

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 burden, and it does compensate: it defines message as a 'Free-text objective' and inputs as an 'Optional JSON string of structured inputs.' This adds meaning beyond the bare schema properties. However, the guidance is shallow—it gives no examples, no JSON shape or expected keys, and no hint about what happens when both are empty (both parameters are optional), leaving an agent to guess at valid invocation patterns.

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 opens with a specific verb and resource: 'Run the crm domain agent action `chat`.' This tells an agent it is invoking a CRM-domain chat/agent action rather than a data-query or object-mutation tool. However, the first sentence largely restates the tool's name, and it does not explicitly differentiate from sibling chat tools (commerce_chat, finance_chat, brain_chat) or the generic dispatch_domain_agent, so it stops short of full sibling 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?

There is no guidance on when to use crm_chat versus alternatives. The description does not say to prefer it for open-ended CRM objectives, nor when to avoid it in favor of structured tools like crm_query_data, crm_lead_qualification, or dispatch_domain_agent. The routing sentence ('Routes through the platform's domain-agent dispatcher') is mechanical context, not usage direction, so an agent is left to infer when this tool applies.

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