Returns all monitored containers with their current state, health status, and basic metadata; filter by agent UUID or use 'local' to inspect server-managed resources.
List all monitored containers with their current state (running, stopped, restarting), health status, and basic metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | No | Filter by agent UUID, or 'local' for resources managed directly by the server. Omit to return all. |
Changes observed during successful MCP inspections.
v1.10.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already tells the agent this is a safe read with no side effects, so the bar is lower. The description does add useful behavioral context by naming what each row contains (current state values running/stopped/restarting, health status, basic metadata), but it says nothing about result volume, pagination, or ordering for what could be a large fleet-wide listing.
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?
One front-loaded sentence with no filler; the resource and the returned fields come immediately. It is efficient, though its economy is partly why usage and filtering context are missing.
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 read-only single-optional-parameter tool with full schema coverage and annotations, this is close to sufficient, and the description usefully enumerates the return fields since there is no output schema. Only fleet-size/pagination behavior is unaddressed.
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% and the single agent_id parameter is fully documented in the schema, including the 'local' sentinel and the omit-to-return-all behavior, so the baseline of 3 applies. The description adds no param meaning beyond that and in fact says 'all' without hinting that a per-agent filter exists.
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?
States a specific verb and resource ('List all monitored containers') plus the scope and the fields returned (state, health, metadata). It does not name the sibling that overlaps most (get_container for details, list_kubernetes_pods for K8s workloads, list_endpoints), so the agent must infer the boundary itself.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named. The only signal is the phrase 'all monitored containers', which lets an agent infer this is a broad enumeration rather than a detail lookup, but the routing decision against get_container or the Kubernetes list tools is left entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.