vizier_verify_actionEvaluate whether an AI agent should be allowed to perform a proposed action.
| Name | Required | Description | Default |
|---|---|---|---|
| agent | Yes | ||
| action | Yes | ||
| context | Yes | ||
| authority | Yes | ||
| principal | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already disclose readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, non-mutating operation. The description ('Evaluate') aligns with these hints but adds no additional behavioral context such as return value shape, error conditions, or side effects. The baseline of 3 applies because the description is consistent with annotations but not informative beyond them.
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?
A single sentence conveys the core purpose without any filler. It is extremely concise and front-loaded, making it easy to parse quickly.
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?
Given the tool's complexity (five required nested objects) and the lack of an output schema, the description is far too minimal. It does not explain the evaluation logic, what constitutes a positive or negative result, or how the parameters relate. An agent would struggle to invoke this tool correctly based solely on the provided text.
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 provides zero explanation of the five required parameters (agent, principal, action, authority, context). The parameter names and nested structure are self-descriptive to some degree, but the description does not compensate for the lack of schema descriptions, leaving an agent without guidance on how to fill these fields correctly.
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 clearly states a specific verb ('Evaluate') and resource ('whether an AI agent should be allowed to perform a proposed action'), making the tool's purpose immediately understandable. It does not need sibling differentiation since no siblings exist, but it lacks a bit of specificity about what 'allowed' means in terms of the evaluation output.
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 provided about when to use this tool versus alternatives, though there are no siblings listed. The description implies it is used for pre-action permission checks but does not state explicit conditions, prerequisites, or exclusions. An agent must infer when to call it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
With only one tool, there is no possibility of confusion or misselection. The tool's purpose is unique and clearly defined by its description.
The single tool name follows a clear verb_noun pattern (verify_action) with a consistent server prefix (vizier_), making it easily interpretable. Consistency is trivially maintained with one tool.
A single tool is borderline for the apparent scope of an action verification service. While focused, the server might benefit from additional supporting tools (e.g., policy listing or decision history), making the count feel slightly thin.
The tool covers the core operation of evaluating an action, which may be sufficient for narrow use cases. However, auxiliary capabilities like explaining decisions or managing policies are missing, leaving minor gaps.