scan_iacScans an infrastructure-as-code folder with Trivy to detect misconfigurations in Dockerfiles, Compose, Kubernetes/Helm, Terraform, CloudFormation, and Azure ARM.
Trivy config: Dockerfile, docker-compose, manifiestos Kubernetes y Helm, Terraform, CloudFormation, Azure ARM.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Carpeta con los archivos de infraestructura | |
| timeout_minutes | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already tells the agent this is a safe non-mutating read, and the description adds nothing beyond that: no note that Trivy must be installed (relevant given sibling xolotl_install), no indication of what findings look like, no mention of how long scans run or how failures surface. The coverage list is scoping, not behavior.
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 short fragment with zero padding, front-loaded with the engine and target list. It is efficient but under-specified rather than genuinely concise, and the missing verb makes it read as a label instead of an instruction.
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 simple two-parameter read-only scanner with no output schema, the description should still convey the action, the timeout's purpose, and the Trivy dependency. None of that is present, leaving the agent to guess how the tool behaves when Trivy is absent or when a scan times out.
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 coverage is only 50%: path is documented in Spanish as the folder holding infrastructure files, but timeout_minutes has no description anywhere. The description mentions neither parameter, so it fails to compensate for the documented gap (e.g. whether path must be a directory vs a file, or how the timeout affects behavior).
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 enumerates the exact IaC artifacts covered (Dockerfile, compose, Kubernetes/Helm, Terraform, CloudFormation, ARM) and names the underlying engine (Trivy config), which lets an agent distinguish it from scan_container_image or scan_static by target type. However, it is a bare noun list with no verb: it never says it scans for misconfigurations, so the purpose is inferred from the tool name rather than stated.
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 when-to-use guidance is given: nothing says to pick this over scan_static for Terraform/K8s files, nor when an agent should prefer scan_container_image. No prerequisites or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.