salesforce_create_opportunity

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

The description adds a little context about routing and scope (JWT, tenant, company), but it does not describe the actual Salesforce-side behavior or consequences. Given the annotations already indicate a non-read-only, non-idempotent, destructive-true operation, the description should at least disclose that this creates or mutates an opportunity record, but it does not. There is no direct contradiction with the annotations, but the description carries very little behavioral weight.

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 block without excessive padding. However, the opening sentence largely restates the tool name and the middle sentence about routing is generic platform context, so some space is used without adding substantive domain 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?

For a tool flagged as open-world, non-idempotent, and destructive, with two parameters and no schema descriptions, this description is under-specified. It lacks enough domain detail to safely and correctly invoke the action, and it does not explain how the free-text message or structured inputs map to an opportunity creation workflow. The output schema covers return values, but the input and invocation context remain incomplete.

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 defines `message` as a free-text objective and `inputs` as an optional JSON string, which is a minimal starting point, but it gives no information about what the structured inputs should contain, what fields are supported, or how to format them. A caller cannot determine what a valid `inputs` payload looks like for creating an opportunity.

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 salesforce domain agent action `create_opportunity`, which identifies the resource and operation by name, but it never explains what creating an opportunity actually does in Salesforce terms. It also does not differentiate itself from sibling tools like salesforce_create_contact or salesforce_update_opportunity_stage beyond the name.

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 tool versus alternatives. The note about routing through the domain-agent dispatcher is architectural context, not usage guidance. It does not mention prerequisites, when not to use it, or how it differs from direct Salesforce tools like salesforce_passthrough or salesforce_create_task.

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