Skip to main content
Glama

Control Plane

by io.cpln

Get Workload Logs

get_workload_logs
Read-onlyIdempotent

Query workload logs from a GVC. Provide structured params (gvc, workload, container, location, filter) OR a raw LogQL query — a raw query REPLACES the structured params, so it must embed ALL labels itself. Available labels: gvc, workload, container, location, provider, replica, stream — replica and stream are only reachable via a raw query. filter is a literal substring match (|=), not regex; for regex use a raw query with |~. Cron workload? Get jobExecutions via list_deployments (with location), then re-query with a raw query scoping replica= plus the execution's time window — embed gvc/workload/location labels in the raw query. Returns structured JSON with timestamps, messages, and labels. Recommended reading before first use: get_cpln_skill("workload-troubleshooting") — the runbook for this tool family (read once per session).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoAbsolute end time (exclusive, ISO 8601).
gvcNoGVC name. Required unless raw `query` is provided.
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.
fromNoAbsolute start time (inclusive, ISO 8601). Overrides `since`. Must be earlier than `to`.
limitNoMaximum log entries to return (default: 30, max: 999).
orderNoSort order (default: "oldest_first").
queryNoRaw LogQL query. REPLACES the structured params entirely, so it must embed ALL labels itself (gvc, workload, location, …) — required for the replica/stream labels, which have no structured param. Not sanitized — use structured params when possible.
sinceNoLookback window as relative duration (default: "1h"). Examples: "30m", "2h", "1d".
filterNoLiteral substring filter (LogQL `|=`) — only return log lines containing this exact text. NOT a regex; for regex matching use a raw `query` with `|~`.
locationNoLocation to filter logs for (e.g., "aws-us-east-1").
workloadNoWorkload name to filter logs for.
containerNoContainer name to filter logs for (e.g., "main", "_accesslog").

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

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds significant behavioral detail: raw query replaces structured params entirely and must embed all labels, filter is a literal substring match (|=) not regex, and replica/stream are only accessible via raw query. It also discloses return shape (structured JSON with timestamps, messages, labels). This exceeds what annotations provide without contradiction.

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 information-dense with no filler. Once the purpose is stated, it covers structured vs raw query, label availability, filter semantics, the cron special case, return type, and a recommended runbook—each sentence adds distinct value. The length is justified by the tool's complexity; it is not bloated.

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?

For a tool with 12 parameters, a raw query mode, and intricate edge cases, the description covers nearly all necessary context: dual modes, special labels, regex handling, cron workflow, return format, and prerequisite reading. Combined with full schema coverage and an output schema, it is complete enough for an agent to invoke correctly.

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

Parameters4/5

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

Schema coverage is 100% for all 12 parameters, so baseline is 3. The description adds meaningful semantic context beyond the schema by explaining the relationship between `query` and structured params (replacement semantics), the exact meaning of `filter` (literal substring vs regex), and which labels are only available via raw query. This is valuable but not a full per-parameter breakdown, so a 4 is merited.

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 'Query workload logs from a GVC', giving a specific verb and resource. It clearly distinguishes this tool from siblings like query_metrics or query_traces by focusing on workload logs, and further clarifies the tool's two modes (structured params vs raw LogQL).

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

Usage Guidelines5/5

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

It gives explicit guidance on when to use structured params versus a raw query, noting that replica and stream labels are only reachable via raw query and that regex requires a raw query. It also provides a specific alternative workflow for cron workloads using list_deployments, and recommends a prerequisite skill. This is thorough and actionable.

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