Skip to main content
Glama

Control Plane

by io.cpln

Query Distributed Traces

query_traces
Read-onlyIdempotent

Search distributed traces (Tempo/TraceQL) — find slow or failing requests across workloads, then drill in with get_trace. Provide structured params (gvc, workload, location, errorsOnly, minDuration) OR a raw traceql query — a raw query REPLACES the structured params, so it must embed ALL filters itself. Span attributes available: resource.gvc, resource.workload, resource.location. Traces exist only where tracing is enabled on the GVC (spec.tracing via update_gvc/create_gvc) and only for sampled requests after enablement. Returns a table of trace IDs with root span, start time, and duration.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoAbsolute end time (exclusive, ISO 8601).
gvcNoFilter traces to one GVC (matches the `resource.gvc` span attribute).
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 traces to return (default: 20, max: 100).
sinceNoLookback window as relative duration (default: "1h"). Examples: "30m", "2h", "1d".
traceqlNoRaw TraceQL query (e.g. `{ resource.workload = "api" && status = error }`). REPLACES the structured params entirely, so it must embed ALL filters itself. Span attributes available: resource.gvc, resource.workload, resource.location.
locationNoFilter traces to one location (e.g., "aws-us-east-1").
workloadNoFilter traces to one workload (matches the `resource.workload` span attribute).
errorsOnlyNoOnly return traces containing at least one error span.
minDurationNoOnly return traces slower than this total duration (e.g., "500ms", "2s") — the slow-request finder.

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

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses that a raw `traceql` query REPLACES structured params, that traces are only present when tracing is enabled and sampled, and that results are a table of trace IDs with root span, start time, and duration. This adds real behavioral context without contradicting 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 two-sentence description is information-dense but efficient; it front-loads the core purpose, then packs interaction rules, prerequisites, and output format without redundancy.

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 complexity of 11 parameters, an output schema, and annotations, the description covers the essential selection guidance, the replace semantics of traceql, the tracing-enabled prerequisite, sampling caveat, and result shape, making it a complete usage summary.

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?

While the schema fully documents each parameter, the description adds critical interaction semantics: raw `traceql` replaces all structured filters, and `minDuration` is framed as the slow-request finder. It also lists available span attributes for query authoring, exceeding schema descriptions.

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 action ('Search distributed traces (Tempo/TraceQL)') and states the purpose ('find slow or failing requests'), explicitly distinguishing itself from the sibling get_trace for drilling into a single trace.

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?

It specifies the use case (find slow or failing requests), names the follow-up alternative (get_trace), and notes a key prerequisite (tracing must be enabled on the GVC). It doesn't enumerate all exclusion cases but gives sufficient context for selection.

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