Evaluate a protected local action, then execute, block, or queue it according to security policy. Enforces least-privilege controls and prompts human approval for sensitive calls.
Evaluate and safely execute, block, or queue a protected local action.
| Name | Required | Description | Default |
|---|---|---|---|
| arguments | Yes | ||
| tool_name | Yes |
Changes observed during successful MCP inspections.
v1.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of explaining behavior. It does disclose three possible outcomes (execute, block, queue), but it omits what evaluation criteria are used, what side effects occur, whether approval is required, and what happens to a blocked or queued 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 a single economical sentence with no obvious filler, but it is under-specified to the point of missing essential operational context. It reads as terse rather than deliberately concise.
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 guarded execution tool with two required parameters, nested arguments, no output schema, and no annotations, the description is far too incomplete. It does not cover return values, approval flow, error behavior, or how this tool relates to siblings such as list_pending_actions and resolve_approval.
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 does not mention tool_name or arguments. The agent receives no guidance on what tool_name should contain, what shape arguments should take, or how the payload relates to the protected action being executed.
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 phrase ('evaluate and safely execute, block, or queue') and names a resource ('protected local action'), so it is not a tautology. However, 'protected local action' is vague and the description does not differentiate it from sibling tools such as evaluate_tool_call or resolve_approval.
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 explicit when-to-use or when-not-to-use guidance is provided. The only implicit signal is the phrase 'protected local action,' but the description never clarifies when this guarded wrapper should be preferred over directly invoking a tool or over sibling tools like resolve_approval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.