Control Plane

Query Distributed Traces

query_traces

Read-onlyIdempotent

Search distributed traces (Tempo TraceQL), newest first, to find slow, failing, or specific requests; drill into one with get_trace. Filter with structured params (gvc, workload, location, httpMethod, requestId, errorsOnly, minDuration) OR a raw traceql query, which REPLACES them and must embed every filter. Span attributes: resource.gvc, resource.workload, resource.location, span.http.method, span.http.url (the full URL), span.http.status_code (a string, e.g. "503"), span."guid:x-request-id". Traces exist only where tracing is enabled (spec.tracing on the GVC via update_gvc, or on the org) and only for requests sampled after that. Returns trace IDs with root span, requests seen, start time, and duration.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	No	Absolute end time (exclusive, ISO 8601).
`gvc`	No	Filter traces to one GVC (matches the `resource.gvc` span attribute).
`org`	No	Organization slug.
`from`	No	Absolute start time (inclusive, ISO 8601). Overrides `since`. Must be earlier than `to`.
`limit`	No	Maximum traces to return (default: 20, max: 100).
`since`	No	Lookback window as relative duration (default: "1h"). Examples: "30m", "2h", "1d".
`traceql`	No	Raw TraceQL, e.g. `{ resource.gvc = "prod" && span.http.url =~ "./checkout." }`. REPLACES the structured params, so it must embed every filter.
`location`	No	Filter traces to one location (e.g., "aws-us-east-1").
`workload`	No	Filter traces to one workload (matches the `resource.workload` span attribute).
`requestId`	No	Only the trace of this request: the x-request-id in access and request logs.
`errorsOnly`	No	Only return traces containing at least one error span.
`httpMethod`	No	Only traces with a request of this HTTP method, e.g. "POST".
`minDuration`	No	Only return traces slower than this total duration (e.g., "500ms", "2s") — the slow-request finder.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes
`data`	No	The full result. Read this, not only the summary.
`details`	No
`summary`	Yes
`nextSteps`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed26 schema fields changedSep 30, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedInput schema / additionalProperties
```
Removed value: -false
```
removedInput schema / properties / from / maxLength
```
Removed value: -40
```
removedInput schema / properties / gvc / minLength
```
Removed value: -1
```

addedInput schema / properties / httpMethod

Added value: +{
+  "description": "Only traces with a request of this HTTP method, e.g. \"POST\".",
+  "type": "string"
+}

removedInput schema / properties / location / minLength
```
Removed value: -1
```
removedInput schema / properties / minDuration / pattern
```
Removed value: -"^\\d+(\\.\\d+)?(ns|us|ms|s|m|h)$"
```

changedInput schema / properties / org / description

Previous value: -"Organization 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."New value: +"Organization slug."

removedInput schema / properties / org / maxLength
```
Removed value: -63
```
removedInput schema / properties / org / minLength
```
Removed value: -1
```

removedInput schema / properties / org / pattern

Removed value: -"^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$"

addedInput schema / properties / requestId

Added value: +{
+  "description": "Only the trace of this request: the x-request-id in access and request logs.",
+  "type": "string"
+}

removedInput schema / properties / since / maxLength
```
Removed value: -20
```
removedInput schema / properties / to / maxLength
```
Removed value: -40
```

changedInput schema / properties / traceql / description

Previous value: -"Raw 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."New value: +"Raw TraceQL, e.g. `{ resource.gvc = \"prod\" && span.http.url =~ \".*/checkout.*\" }`. REPLACES the structured params, so it must embed every filter."

removedInput schema / properties / traceql / maxLength
```
Removed value: -500
```
removedInput schema / properties / traceql / minLength
```
Removed value: -1
```
removedInput schema / properties / workload / minLength
```
Removed value: -1
```
removedInput schema / required
```
Removed value: -[
-  "org"
-]
```

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / additionalProperties
```
Removed value: -false
```

changedOutput schema / properties / data / description

Previous value: -"The full machine-readable result — list rows, the resource object, query results. Read THIS, not just the summary."New value: +"The full result. Read this, not only the summary."

addedOutput schema / properties / details
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / nextSteps / description

Removed value: -"Recommended follow-up actions for this task, in order."

removedOutput schema / properties / ok / description
```
Removed value: -"Whether the call succeeded."
```
removedOutput schema / properties / summary / description
```
Removed value: -"One-line summary of the result."
```

AddedAug 14, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses real behavioral traits: newest-first ordering, the mutually exclusive traceql-vs-structured filter mode, and critically the enablement/sampling caveat that explains why results may be empty. This is exactly the kind of context annotations cannot carry.

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?

Purpose and the get_trace handoff are front-loaded, and the sentences are dense but informative. The trailing 'Returns trace IDs with root span, requests seen, start time, and duration' duplicates the output schema, which is minor waste but keeps it from a perfect score.

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 13-parameter tool with two query modes and an enablement dependency, the description covers ordering, mode interaction, filterable attributes, and the tracing prerequisite. With an output schema present, it needn't detail return values further, and nothing an agent needs to call it correctly is missing.

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%, so the baseline is 3; the description goes further by mapping filterable span attributes (resource.gvc, span.http.url, span.http.status_code as a string e.g. "503", span."guid:x-request-id") that an agent needs to author TraceQL. Some of the traceql-override wording repeats the schema, but the attribute mapping is net-new value.

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 and resource ('Search distributed traces (Tempo TraceQL)'), gives the default ordering ('newest first'), and explicitly routes to the sibling drill-down tool ('drill into one with get_trace'). An agent can distinguish it from get_trace without opening either schema.

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?

Names the use cases ('find slow, failing, or specific requests'), points to the alternative for drilling deeper, and explains the enabling prerequisite ('Traces exist only where tracing is enabled ... and only for requests sampled after that'). It also clarifies when to prefer structured params versus a raw traceql query.

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

All Control Plane tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.