Skip to main content
Glama

traces_search

Search distributed traces across observability backends to find requests by service, operation, tags, time window, duration, or error state. Narrow results with provider-native queries and filters.

Instructions

Search distributed traces. Backend: Jaeger. Param semantics vary by provider: service works for jaeger/zipkin/skywalking (skywalking expects a service id); query is a provider-native raw query (Tempo TraceQL).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "traces_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoJSON-encoded tag filter (Jaeger only)
limitNoMax traces to return
queryNoProvider-native raw query (Tempo TraceQL)
stateNoTrace state filter (SkyWalking)
serviceNoService name (jaeger/zipkin) or service id (skywalking)
lookbackNoTime window (e.g. "1h", "30m", "2d")1h
operationNoOperation/span/endpoint name filter
max_durationNoMaximum duration (Jaeger only)
min_durationNoMinimum duration (e.g. "500ms", "1s")
annotation_queryNoZipkin annotation query (e.g. "http.status_code=500 and error")

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations at all, the description carries the full burden and discloses only the backend dispatch model and provider-dependent parameter meaning. It never states that this is a read-only operation, whether results are paginated/capped beyond `limit`, what auth is needed, or what a response looks like. It also opens with 'Backend: Jaeger' while the rest of the text describes zipkin/skywalking/Tempo behavior, which is internally confusing about which backend actually serves a given call.

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?

Two tight sentences, front-loaded with purpose before the provider caveats, with no filler. The only structural weakness is leading with a single 'Backend: Jaeger' claim that the second clause then complicates.

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

Completeness3/5

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

For a 10-parameter, zero-required search tool with no output schema and no annotations, the definition covers the provider-variance complexity but omits call-shaping essentials: default behavior, whether a filter is needed to avoid unbounded scans, and result/pagination characteristics. Schema descriptions fill in per-parameter applicability, so it is adequate but not complete.

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 coverage is 100%, so every parameter already has a description, and the description's notes on `service` and `query` largely restate the schema ('Service name (jaeger/zipkin) or service id (skywalking)', 'Provider-native raw query (Tempo TraceQL)'). It adds the useful framing that semantics vary by provider, but does not clarify the nine other params or how filters combine.

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

Purpose4/5

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

The description gives a specific verb and resource ('Search distributed traces') plus the backing system ('Backend: Jaeger'), which is enough to separate it from siblings like traces_services or trace_get. It stops short of naming an alternative sibling or stating the single-trace-vs-search distinction explicitly.

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?

Usage is only implied: the reader infers this is the exploratory/multi-result trace tool and that provider-specific params govern correctness. There is no explicit when-to-use versus trace_get or traces_operations, and no statement that no parameters are required, leaving the agent to guess a sensible default query.

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