Skip to main content
Glama

Control Plane

by io.cpln

Workload — Stop a Replica

workload_stop_replica
Destructive

Terminate a single running replica (pod) of a workload by issuing a stopReplica command — useful to recycle a wedged or unhealthy replica. The platform reschedules a replacement per the workload’s scaling, so this interrupts only in-flight work on that one replica; it does not delete the workload or any persistent data. Discover replica names with list_workload_replicas, and pass a location where the workload is deployed (list_deployments). The resulting command is trackable with get_command / list_commands.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gvcYesGVC slug (lowercase kebab-case). Use the GVC the user named; otherwise discover with list_resources (kind="gvc") and let them choose — never guess (a wrong GVC targets the wrong environment).
orgYesOrganization slug (lowercase kebab-case). NEVER guess — if the user has not named one, ask. On org-not-found, stop and ask; do not retry variants.
nameYesWorkload name (lowercase kebab-case, must start with a letter, max 49 chars, cannot end with -headless). The name is IMMUTABLE — "renaming" requires delete + recreate (loses public URL, internal DNS, policy targetLinks).
replicaYesExact replica (pod) name to terminate. Discover names with list_workload_replicas.
locationYesLocation where the replica runs — must be a location where this workload is deployed (see list_deployments).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether the call succeeded.
dataNoThe full machine-readable result — list rows, the resource object, query results. Read THIS, not just the summary.
summaryYesOne-line summary of the result.
nextStepsNoRecommended follow-up actions for this task, in order.

TDQS

A4.5/5.0
Behavior5/5

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

The annotations already flag destructiveHint=true, but the description adds crucial nuance: it interrupts only in-flight work on that one replica, the platform reschedules a replacement, and persistent data remains intact. This tells an agent exactly the blast radius beyond the structured annotations.

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

Conciseness5/5

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

The description is compact and front-loaded with the purpose, followed by consequences, discovery guidance, and tracking information. Every sentence earns its place; there is no filler or repetition of schema fields.

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 the five required parameters and destructive behavior, the description covers why to use the tool, what happens after (replica scheduling), what doesn't get affected, and which companion tools to use. An output schema exists, so return-value details can be left to the schema. This is sufficient for an agent to select and invoke the tool correctly.

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

Parameters3/5

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

Schema description coverage is 100%, and all parameters already have meaningful field descriptions, including warnings against guessing gvc/org. The tool description reinforces the new for replica and location but adds little new semantic information beyond the schema. Baseline 3 is appropriate when the schema carries the heavy lifting.

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?

The description opens with a specific verb and resource: "Terminate a single running replica (pod) of a workload by issuing a `stopReplica` command." It clearly distinguishes this from workload_start_cron and other workload-related siblings, and clarifies what it does not do (does not delete the workload or persistent data).

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

Usage Guidelines4/5

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

Context is clear: use it to recycle a wedged or unhealthy replica, and the description names discovery and tracking tools (list_workload_replicas, list_deployments, get_command/list_commands). However, it does not explicitly state when not to use it or name a direct alternative for stopping the whole workload, so it stops short of a full 5.

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

All Control Plane toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Every tool targets a distinct resource/action pair (e.g., get_resource vs get_resource_schema, list_deployments vs list_workload_replicas) and descriptions clearly differentiate purposes. No two tools appear to do the same thing.

Naming Consistency5/5

All tools follow a verb_noun snake_case pattern (create_gvc, update_workload, list_resources, query_metrics) with consistent verbs. The few imperative verbs (browse, build, mount) still maintain the same verb-first structure.

Tool Count1/5

With 55 tools, this server far exceeds the typical well-scoped 3-15 tool range. While each tool appears purposeful, the sheer number creates selection overhead and falls into the extreme 50+ category on the rubric.

Completeness4/5

The surface covers nearly the full Control Plane lifecycle: CRUD for GVC, workload, identity, policy, volumeset, and domain, plus observability, templates, image builds, and Terraform. Minor gaps include referenced but missing configure_workload_* tools and no secret creation/deletion (by design).

Resources