Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Get Trace Details

get_trace_details
Read-only

Fetch a Sentry trace overview by trace ID, including statistics, span breakdown, and a Sentry link, to inspect trace performance without listing every span.

Instructions

Get an overview of one Sentry trace by trace ID: trace statistics, a span breakdown, and a link to the trace in Sentry. Shows a condensed subset of spans, not every span; to list all spans in a trace, use search_traces.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "traceId": "<traceId>"
    },
    "name": "get_trace_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
freshNoBypass cached reads.
spanIdNoA span ID in the trace to focus on; omit for the trace overview.
traceIdYesThe 32-character hex trace ID.
regionUrlNo
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, non-destructive, open-world behavior, so the description's contribution is the completeness caveat: results are a condensed subset of spans, not exhaustive. It also names the three components of the response, which is meaningful behavioral context given there is no output schema. It does not mention caching semantics despite a `fresh` parameter, but that is a minor gap.

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?

Two sentences, front-loaded with the primary action and return contents, followed by the disambiguation pointer. No filler or restated title text.

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

Completeness4/5

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

With no output schema, the description usefully sketches the return payload (statistics, span breakdown, link), which is what an agent most needs to interpret results. Region/organization parameters are explained in the schema, so the only remaining omission is caching behavior tied to `fresh`.

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 80%, already documenting traceId format, spanId focus/omit semantics, fresh, regionUrl, and organizationSlug. The description only restates that lookup is by trace ID and does not clarify interaction between spanId focus and the overview mode. Baseline 3 is appropriate when the schema carries the detail.

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 ('Get an overview of one Sentry trace by trace ID') and enumerates what comes back: trace statistics, span breakdown, and a Sentry link. It also distinguishes itself from search_traces, so an agent can choose between them 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 Guidelines4/5

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

Explicitly routes the agent to search_traces when the goal is listing all spans, and warns that this tool shows only a condensed subset. That is a clear use/avoid condition; it stops short of only-tool-level exclusions such as when a single span lookup (get_span_details) is preferable.

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