provider.external_action

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds useful behavioral context: it requires local user approval, disallows self-approval, retries the same request ID after user approval, and notes that per-request argument checks and session policy apply. This goes beyond annotations, though it does not elaborate on what is destroyed or the full side effects of the action.

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 concise, consisting of two sentences. It front-loads the command name and then presents risk and approval details. While the structure is not ideal—it leads with internal metadata rather than the tool's function—it is free of fluff and efficiently communicates the approval flow.

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 9 parameters, nested objects, and an output schema, the description is insufficient. It fails to explain the purpose of the action, how parameters relate, or what the expected outcome is. The agent would struggle to construct a valid request or understand the tool's behavior, especially given its destructive nature.

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?

The description provides no elaboration on any of the 9 parameters. Schema descriptions cover only 56% of parameters, and the description does not compensate for the undocumented ones. It does not clarify the meaning of `action`, `providerId`, or other fields beyond what the schema already offers, leaving gaps for the agent.

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 identifies the tool as a Blender Harness command `provider.external_action` but never explains what 'external_action' actually does. It mentions risk gating and approval but omits the core operation, leaving the agent to guess the tool's function. It does not differentiate it from sibling tools like `provider_query` or `provider_query_result`.

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 description states that local user approval is required and that a client cannot approve its own request, but it does not specify any conditions for selecting this tool over other provider-related tools. There is no mention of alternatives or contextual prerequisites beyond the approval flow.

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