Intercept and evaluate AI agent tool calls against out-of-band AST circuit breaker policies.
| Name | Required | Description | Default |
|---|---|---|---|
| payload | Yes | Serialized parameters or code payload | |
| tool_name | Yes | Target tool name to execute |
Changes observed during successful MCP inspections.
Input schema / properties / agent_idRemoved value: -{
- "default": "agent_planner",
- "type": "string"
-}Input schema / properties / payload / descriptionPrevious value: -"Raw serialized invocation arguments, commands, or python code"New value: +"Serialized parameters or code payload"Input schema / properties / tool_name / descriptionPrevious value: -"The target tool function name proposed by the agent"New value: +"Target tool name to execute"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and fails to disclose key behaviors: whether the target tool is actually executed on policy pass, what happens on policy failure (error, blocked response), whether side effects occur, and what is returned. The phrase 'out-of-band AST circuit breaker policies' is opaque and does not compensate for the lack of behavioral detail.
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, front-loaded sentence with no wasted words. However, the conciseness comes at the cost of clarity due to unexplained jargon.
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 security-sensitive execution gate with no output schema and no annotations, the description omits critical information: what the tool returns, error semantics on policy violation, and whether execution is performed. An agent cannot confidently invoke this tool or interpret its results.
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 100%, with both 'tool_name' and 'payload' explicitly described. The description adds no extra meaning beyond the schema, so the baseline of 3 applies.
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 states a verb and resource ('Intercept and evaluate AI agent tool calls') but uses jargon ('out-of-band AST circuit breaker policies') and never clarifies whether the tool also executes the target tool or only evaluates it. The name suggests execution, yet the description only mentions interception/evaluation, leaving ambiguity for the agent.
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 calling the target tool directly or versus the sibling attestation tool. The only implied usage is that it is for protected tool calls, but there is no explicit context or exclusion.
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.