Skip to main content
Glama
yunusemregul

dynatrace-bridge-mcp

by yunusemregul

get_trace_details

Fetch comprehensive details for a single Dynatrace trace call: exceptions, method tree, downstream calls, SQL, and headers. Use it to debug or analyze a specific trace node.

Instructions

Everything Dynatrace recorded about one call (node) of a trace: exceptions with stack traces (identical ones grouped into one entry with a count), the code-level method tree with total / self / CPU / wait time pruned to the hot paths, the downstream calls it made with SQL text and call counts, the full SQL of a database call, HTTP request and response headers and parameters, the process and host / pod it ran on, and the technologies involved.

Pass call_uri of a node as printed by get_trace (or by list_traces for the entry call), with a time window that contains the trace. Stack traces show the top stack_frames frames (full_stack: true for all) of the exception_limit most frequent distinct exceptions. Every section has its own share of the output, so a long one cannot crowd out the others. The method tree hides methods below min_method_ms (default 1 % of the call) and pass-through frames, and says how many. Authorization, cookie and token headers are never shown; request parameters, headers and attributes whose name looks like a secret (password, token, key, session id, …) or whose value looks like a credential are printed as <masked>, as are such parameters inside URLs; ordinary parameters are shown as Dynatrace stored them (Dynatrace itself may already have replaced values by <masked>).

This tool runs through the Dynatrace Bridge browser extension in the user's logged-in browser. If it fails, report the error to the user; do not try to open browser tabs or use browser automation instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of downstream calls to print. Default 25, at most 200. The output says how many were omitted.
time_toNoAbsolute end time, ISO 8601; without a zone it is read as UTC. Without time_from, the window starts minutes_lookback before this. Must not be in the future.
call_uriYesThe callURI of the call, as printed by get_trace or list_traces.
time_fromNoAbsolute start time, ISO 8601 (e.g. '2026-09-23T10:28:00Z'). A timestamp without a zone (Z or ±hh:mm) is read as UTC. Without time_to, the window runs from here to now. Must not be in the future.
full_stackNoPrint every frame of the exception stack traces. Default false.
environmentNoWhich Dynatrace environment to query, as named in the Dynatrace Bridge extension popup. Omit it for the default, the first environment configured there. The names are not listed here because the extension had not connected yet when this description was built; `dynatrace_bridge_status` lists them.
method_limitNoMaximum lines of the code-level tree. Default 40, at most 300.
stack_framesNoFrames per stack trace when full_stack is not set. Default 8, at most 100.
min_method_msNoHide methods of the code-level tree that took less than this many milliseconds. Default: 1 % of the call's response time, at least 1 ms.
exception_limitNoMaximum distinct exceptions printed with their stack trace, most frequent first. Default 8, at most 50.
minutes_lookbackNoWindow length in minutes. Default 120. With neither time_from nor time_to it means the last N minutes up to now; with only time_to it means the N minutes ending at time_to; ignored when time_from is given. The response header always shows the resolved absolute UTC window.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: secret/credential parameters and headers are masked, auth/cookie/token headers are never shown, each output section gets its own share so one cannot crowd out others, the method tree hides sub-threshold and pass-through frames and reports how many were hidden, and the tool depends on the user's logged-in browser via the Dynatrace Bridge extension. These are exactly the behavioral traits an agent cannot infer from the schema.

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 is front-loaded, followed by invocation, then output/parameter behavior, then the operational caveat, with no filler sentences. It is long, and the parameter paragraph partly restates schema defaults (limits, caps), which slightly dilutes density for an otherwise tight definition.

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 an 11-parameter tool with no output schema and no annotations, the description covers what is returned section by section, how output is bounded, how secrets are masked, and the browser-extension execution model. An agent has enough to call it correctly and to interpret the result.

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, but the description adds meaning beyond the schema: min_method_ms also drops pass-through frames and the output reports the hidden count, the time parameters resolve to a stated absolute UTC window in the response header, and lookback interacts with time_from/time_to. These go beyond the per-field schema text.

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 opening sentence states a specific verb+resource (retrieve everything recorded about one trace node) and then enumerates exactly what that includes: exceptions with stack traces, the method tree, downstream calls, SQL, HTTP headers, host/process, technologies. This clearly distinguishes it from get_trace (which prints nodes) and list_traces (which prints entry calls).

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 gives concrete invocation context: pass the call_uri as printed by get_trace or list_traces, with a time window containing the trace, establishing the get_trace -> get_trace_details flow. It also gives failure guidance (report the error, don't fall back to browser automation). It stops short of explicitly saying when NOT to use it versus trace_statistics or analyze_* siblings.

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