Kubernetes Tools MCP Server

get_daemonset_summaries

List DaemonSet summaries in a namespace or across all namespaces to check desired, ready, and scheduled pod counts per node and spot rollout shortfalls.

Instructions

Retrieves a list of DaemonSetSummary objects for DaemonSets in a given namespace or all namespaces, similar to kubectl get daemonsets -o wide.

A DaemonSet runs one pod on each node it targets; its pods are named
"<daemonset>-<5 characters>" and have `owner` "DaemonSet/<daemonset>" in
`get_pod_summaries`. A shortfall between the counts below ("desired 5,
ready 4") is often the first sign of a problem with a particular node.

Parameters
----------
namespace : Optional[str], default=None
    The specific namespace to list DaemonSets from. If None, lists from all
    namespaces.

Returns
-------
list of DaemonSetSummary
    A list of DaemonSetSummary objects, each with the following fields:

    name : str
        Name of the DaemonSet.
    namespace : str
        Namespace in which the DaemonSet runs.
    desired_number_scheduled : int
        Number of nodes that should be running the DaemonSet's pod - the
        actual number of nodes it targets.
    current_number_scheduled : int
        Number of nodes running at least one of its pods that should.
    number_ready : int
        Number of nodes whose pod is ready.
    updated_number_scheduled : int
        Number of nodes running a pod from the current pod template. Less
        than desired means a rollout is in progress or stuck.
    number_available : int
        Number of nodes whose pod has been ready for at least minReadySeconds.
    number_misscheduled : int
        Number of nodes running its pod that should not be.
    node_selector : dict[str, str]
        The pod template's nodeSelector (kubectl's NODE SELECTOR column).
        Many DaemonSets choose their nodes with node affinity and
        tolerations instead, which this does not show, so an empty selector
        does not mean "every node"; desired_number_scheduled is the count.
    update_strategy : str
        Update strategy type ("RollingUpdate" or "OnDelete").
    images : list[str]
        Container images of the current pod template, in container order. A
        pod running a different image is from an earlier revision.
    age : datetime.timedelta
        Age of the DaemonSet (current time minus creation timestamp).

Raises
------
K8sConfigError
    If unable to initialize the K8S API.
K8sApiError
    If the API call to list DaemonSets fails.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`namespace`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.1.0Oct 4, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it does so well: it declares the read-only retrieval nature, documents both raised errors (K8sConfigError, K8sApiError), and adds a non-obvious caveat that node_selector being empty does not mean 'every node' because affinity/tolerations are not shown. It omits RBAC/permission and pagination behavior, keeping it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose, then a semantic aside, then Parameters/Returns/Raises sections, so key information comes first. It is lengthy and the entire Returns field list partially duplicates the existing output schema, but most field notes (e.g., node_selector caveat, updated_number_scheduled meaning a stalled rollout) add interpretation that earns their place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a single optional parameter, an existing output schema, and no annotations, the description covers everything an agent needs: purpose, kubectl analogy, parameter semantics, error conditions, and diagnostic interpretation of the counts. Nothing required for a correct call is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there is one parameter, yet the description fully defines it: 'The specific namespace to list DaemonSets from. If None, lists from all namespaces.' This completely compensates for the undocumented schema and disambiguates the null default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Retrieves a list of DaemonSetSummary objects for DaemonSets') with scope ('in a given namespace or all namespaces'), and grounds it against a familiar reference ('similar to kubectl get daemonsets -o wide'). This clearly distinguishes it from siblings like get_deployment_summaries, get_statefulset_summaries, and get_replicaset_summaries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Offers diagnostic context ('a shortfall between the counts below is often the first sign of a problem with a particular node') and cross-references get_pod_summaries for pod naming/owner, which implies usage. However, it never explicitly states when to choose this over the sibling summary tools or any when-not conditions, so selection is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.