Skip to main content
Glama
yunusemregul

dynatrace-bridge-mcp

by yunusemregul

analyze_response_time

Break down Dynatrace service response time to pinpoint slow endpoints, costly downstream calls, database statements, and outliers.

Instructions

Shows where the response time of a service goes and how it is distributed (Dynatrace response time analysis). Part 1, hotspots: average response time split into own code, calls to other services and database calls; code execution time by state (CPU, wait, lock, network and disk I/O, suspension); every downstream service and database with its contribution, call frequency and call time; and the single downstream requests / SQL statements that cost the most. Part 2, distribution: a text histogram of response times including failed requests, with the outlier tail called out.

Start here for "why is this service (or one of its endpoints) slow". Pass service as an id or a name. The shared trace filters (response_time_min_ms, response_time_max_ms, http_code, failed, http_method, request, request_group_id, url_contains, request_kind, raw_filters) narrow the analysed requests. E.g. response_time_min_ms: 2000 analyses only the slow requests, request one endpoint. It runs two analysis requests, one after the other. Follow up with service_flow for the full downstream tree, top_database_statements on a database listed here, method_hotspots for own-code time, or list_traces with response_time_min_ms for the outliers.

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 services, and downstream requests / statements to print. Default 15, at most 100. The output says how many were omitted.
failedNotrue = only failed requests, false = only successful requests. Omit for both.
requestNoOne request (endpoint, SQL statement, job) of `service`: its name or a part of the name (e.g. '/cart/checkout'), or its SERVICE_METHOD-… id. A name is looked up among the requests of `service` (one extra request), so it needs `service`; several matches return the candidates instead of guessing. An id works without a lookup.
serviceYesThe service, as an entity id (SERVICE-1234567890ABCDEF) or a name. A name that matches several entities returns the candidates instead of guessing.
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.
http_codeNoHTTP response code filter: one code ('404'), a class ('4xx', '5xx') or a range ('400-599').
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.
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.
http_methodNoHTTP method of the request.
raw_filtersNoEscape hatch for servicefilter types without a dedicated argument. Each entry is {type, values}; type is a numeric id or one of CPU_TIME, CALL_INSTANCE_ID, CALL_TREE, CALL_URI, CALL_TAG, WAIT_TIME, SYNC_TIME, SUSPENSION_TIME, CALLEE, CALLER, PROXY, SERVICE_ID, EXCEPTION, DATABASE_STATEMENT, DATABASE_TABLE, FLAWS, DISK_IO_TIME, NETWORK_IO_TIME, NUMBER_OF_DB_CALLS, NUMBER_OF_NON_DB_CALLS, TIME_SPENT_IN_DB_CALLS, TIME_SPENT_IN_NON_DB_CALLS, TRACE_ID, THREAD_NAME, PROCESSING_TIME, DATABASE_VENDOR, DATABASE_NAME, ENTITY_TAG, PG_NAME, PG_TAG, DATABASE_ROW_COUNT, DATABASE_FETCH_COUNT, WEBREQUEST_HOSTNAME, KEY_REQUEST, RELEASE, BUILD, STAGE, PRODUCT, SPAN_NAME, SPAN_ATTRIBUTE, ENTRY_POINT. Value formats of these types are not verified; time values are microseconds.
request_kindNoweb = only requests of web request and web services (HTTP endpoints, including calls to unmonitored hosts); database = only SQL statements. Omit for every kind (also background activity, custom and messaging services).
url_containsNoOnly web requests whose URL contains this text. The quick way to filter by a URL path fragment (e.g. '/checkout') without knowing the service or the request: it works with or without `service`. It matches nothing for non-web requests (SQL statements, cron jobs, messaging, custom services), which have no URL; use `request` for those.
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.
request_group_idNoA request type as a SERVICE_METHOD_GROUP-… id. For a 'Requests to unmonitored hosts' service this id is the target host (printed by list_service_requests; there the host name can also be passed as `request`).
request_group_nameNoDisplay name belonging to request_group_id, exactly as printed next to the id. Pass it together with request_group_id.
response_time_max_msNoOnly requests whose response time is at most this many milliseconds.
response_time_min_msNoOnly requests whose response time is at least this many milliseconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.8/5.0
Behavior5/5

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

No annotations exist, so the description carries the full burden and does so: it discloses that two analysis requests run sequentially, that it executes through the Dynatrace Bridge browser extension in the user's logged-in browser, and instructs the agent to report failures rather than fall back to browser automation. It also previews what the output contains, including that omitted items are counted.

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?

Front-loaded with the purpose before usage and follow-ups, and every paragraph serves a distinct job (what it shows, when to use it, where to go next). It is dense and long, but for a 17-parameter analysis tool the length is largely earned rather than padded.

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 complex multi-part analysis tool with no output schema, the description still explains the return structure (hotspot breakdown, histogram, outlier tail, omission counts), the filter surface, the browser dependency and the failure path. An agent has enough to call it correctly and interpret the result without further documentation.

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 baseline is a 3, but the description adds genuine value by grouping the 'shared trace filters' and giving usage examples (`response_time_min_ms: 2000`, `request` for a single endpoint) that explain intent rather than restating the schema. It does not clarify the interaction between time_from/time_to/minutes_lookback or the filter precedence, which the schema already handles in 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?

Opens with a specific verb and resource: 'Shows where the response time of a service goes and how it is distributed', then enumerates the two analysis parts (hotspot breakdown and response-time histogram). It also distinguishes itself from siblings by naming service_flow, method_hotspots, top_database_statements and list_traces as different tools.

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?

Explicitly states when to reach for it ('Start here for "why is this service (or one of its endpoints) slow"') and which filters apply in which situation, with a concrete example (`response_time_min_ms: 2000` analyses only slow requests). It also routes the agent onward with named follow-ups for each sub-question.

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