flux_get_app_statsRetrieve CPU, memory, and network stats for an app's containers on a specific node using its owner key. Monitor container performance and resource usage.
CPU, memory and network stats of the containers of an app on one node. Requires the owner key.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| nodeIp | No | ||
| component | No | Component name for multi-component apps. |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does add two genuine behavioral facts beyond the name: the operation is 'live' (real-time sampling) and it requires the owner key. However, it says nothing about error behavior for stopped/missing apps, per-node scoping limits, or rate limits, so meaningful gaps remain.
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?
Two short sentences, front-loaded with the resource being fetched, and the prerequisite placed second. Nothing is wasted, though the extreme terseness leaves gaps that the other dimensions penalize.
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?
With no output schema and no annotations, the description must explain what the caller gets back and under what conditions it works. It never describes the stats payload shape, the per-node output structure, or what happens when the app is not running, leaving an agent under-equipped for a three-parameter tool.
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 33% (only 'component' is documented). The description indirectly compensates: 'on one node' points at nodeIp and 'containers of an app' signals the component granularity. It still gives no syntax for the node IP or component naming and never clarifies the required 'name' or default-node 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?
States a specific verb (get) and resource (CPU/memory/network stats of containers for an app on a node), which clearly distinguishes it from siblings such as flux_get_app_logs, flux_get_app, or flux_get_network_info. It doesn't explicitly name an alternative, but the resource is unambiguous.
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 only usage guidance is an implied prerequisite ('Requires the owner key') and the title's hint that the instance must be running. There is no statement of when to use this versus flux_get_app, flux_get_network_info, or flux_get_app_logs, and no conditions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.