Inspect untrusted MCP/tool output before it enters agent context or triggers an action; 0.002 USDC.
| Name | Required | Description | Default |
|---|---|---|---|
| output | Yes | ||
| policy | No | ||
| source | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / examplesAdded value: +[
+ {
+ "output": {
+ "text": "Quarterly result: 42"
+ },
+ "policy": {
+ "max_bytes": 262144
+ },
+ "source": {
+ "tool": "remote_search"
+ }
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the 0.002 USDC cost, which is a real behavioral trait an agent should know before invoking. However it never clarifies whether the tool merely reports findings or actively blocks/rewrites output, which is core to a 'firewall'.
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 front-loaded sentence with no wasted words, and the call-to-action framing plus price are compactly placed. It is arguably too terse for a tool with nested-object parameters, but it is efficiently structured.
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?
An output schema exists so return values need not be described, but with zero annotation coverage, three parameters including two nested objects, and no explanation of enforcement behavior or policy semantics, the description leaves major gaps for an agent trying to call this correctly.
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% across three parameters, two of them nested objects (policy, source). The description only weakly implies that the required 'output' argument is the untrusted content being inspected; it says nothing about what policy controls or what source identifies. This falls well short of compensating for the coverage gap.
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 gives a specific verb ('Inspect') and resource ('untrusted MCP/tool output'), plus the decision point it guards ('before it enters agent context or triggers an action'). That distinguishes it reasonably well from neighbors like tool_result_schema_validator or secret_redaction_preflight, though no sibling is named explicitly.
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?
The timing guidance ('before it enters agent context or triggers an action') implies when to call it, but there are no explicit exclusions or named alternatives among the many preflight/guard siblings. An agent must infer whether this subsumes or complements tools like tool_result_schema_validator.
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.