Skip to main content
Glama

Get Test Run Details

get_run_details
Read-only

Retrieve complete summary details for one or more test runs, including result counts, timing, git/CI metadata, Playwright settings, shards, re-runs, and quarantine status.

Instructions

Get the summary of one or more test runs: result counts, timing, git branch and commit, CI pipeline, Playwright settings, shards, re-runs and quarantine. It does not list the run's tests: use list_testcase with by_testrun_id for those. Use testrun_id for ID-based lookup or counter for the human-readable run number (e.g. counter="47"). Batch up to 20 runs by comma-separating: testrun_id="id1,id2,id3". Typical workflow: list_testruns() → pick IDs → get_run_details() for the specific run. When is_swarm is true the run was distributed across multiple CI machines and the response also carries machines[] (per-machine counts plus spec_files, duration_ms and idle_tail_ms), machine_summary (machine_count, slowest, fastest, imbalance_ratio) and could_not_execute_specs — specs no machine could run, which means the run is not a clean pass whatever the counts say. Use the optimize_swarm prompt to turn those into a verdict; a file never splits across machines, so a slowest machine running one spec file is a hard floor that more machines cannot beat. Set include_ai_insights=true (single testrun_id only) to also get the run's AI Insights under ai_insights: AI failure categorization (flaky/bug/ui_change), failure clusters, new-failures cards, the error-analysis table, and the LLM-written run summary. AI payloads are generated lazily — if ai_insights sections report status "processing"/"not_generated", poll get_ai_insights(testrun_id=...) until "completed" instead of re-calling this tool. An "unavailable" section carries the upstream statusCode: a 5xx or timeout is transient (retry once via get_ai_insights), a 4xx (bad ids) is terminal.

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": {
      "projectId": "<projectId>"
    },
    "name": "get_run_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
counterNoRun counter. Number for a single run (e.g. 47), or comma-separated string ("47,48,49", max 20) for batch lookup.
projectIdYesProject ID
testrun_idNoSingle test run ID, or comma-separated IDs (max 20)
include_ai_insightsNoAttach the run's AI Insights (categorization, clusters, error-analysis table, written summary) under `ai_insights`. Requires a single testrun_id (not counter, not a batch).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv2.2.0
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / counter / description
      Previous value: -"Run counter. A number for a single run (e.g. 47), or a comma-separated string ('47,48,49', max 20) for a batch."New value: +"Run counter. Number for a single run (e.g. 47), or comma-separated string (\"47,48,49\", max 20) for batch lookup."
    • changedInput schema / properties / counter / type
      Previous value: -[
      -  "number",
      -  "string"
      -]New value: +[
      +  "string",
      +  "number"
      +]
    • changedInput schema / properties / include_ai_insights / description
      Previous value: -"Attach the run's AI Insights (failure categorization, clusters, error-analysis table, LLM summary) under `ai_insights`. Requires a single testrun_id (not counter, not a batch). If a section reports `processing`, poll get_ai_insights(testrun_id=...) instead of re-calling this tool."New value: +"Attach the run's AI Insights (categorization, clusters, error-analysis table, written summary) under `ai_insights`. Requires a single testrun_id (not counter, not a batch)."
    • changedInput schema / properties / projectId / description
      Previous value: -"Project ID (Required). The TestDino project identifier."New value: +"Project ID"
    • changedInput schema / properties / testrun_id / description
      Previous value: -"Test run ID(s). Single ID or comma-separated for batch (max 20). Example: 'test_run_123' or 'run1,run2,run3'."New value: +"Single test run ID, or comma-separated IDs (max 20)"
  2. Changed3 schema fields changedv2.0.2
    • changedInput schema / properties / counter / description
      Previous value: -"Filter by test run counter (sequential number)."New value: +"Run counter. A number for a single run (e.g. 47), or a comma-separated string ('47,48,49', max 20) for a batch."
    • changedInput schema / properties / counter / type
      Previous value: -"number"New value: +[
      +  "number",
      +  "string"
      +]
    • addedInput schema / properties / include_ai_insights
      Added value: +{
      +  "description": "Attach the run's AI Insights (failure categorization, clusters, error-analysis table, LLM summary) under `ai_insights`. Requires a single testrun_id (not counter, not a batch). If a section reports `processing`, poll get_ai_insights(testrun_id=...) instead of re-calling this tool.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Well beyond the readOnly/non-destructive annotations, it discloses conditional response shape (is_swarm adds machines[], machine_summary, could_not_execute_specs), the semantic weight of could_not_execute_specs (run is not a clean pass), the file-never-splits constraint, and AI payload laziness with processing/not_generated/unavailable statuses plus 5xx-vs-4xx retry guidance.

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 purpose and the not-this-tool exclusion, and nearly every clause carries operative information. It is dense rather than wasteful, though the swarm and AI-insights passages run long enough that a reader must work through subordinate clauses to find the trigger conditions.

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?

There is no output schema, so the description carries the burden of describing returns, and it does: named top-level fields, the swarm-specific sub-objects, and the AI insights sections. For a 4-parameter read tool with conditional response shapes, an agent has everything needed to call it and 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% and already documents counter/testrun_id batching and the single-ID restriction on include_ai_insights, so much of the description restates the schema. It still adds real meaning with the concrete counter="47" example, the batch syntax sample, and the explicit note that counter and batch are excluded for AI insights.

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 plus the exact payload: "Get the summary of one or more test runs: result counts, timing, git branch and commit, CI pipeline, Playwright settings, shards, re-runs and quarantine." It also explicitly carves out what it does not return and names the sibling (list_testcase with by_testrun_id) that does.

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?

Gives explicit selection rules: testrun_id for ID lookup vs counter for the human-readable number, comma-separated batching up to 20, and a typical workflow (list_testruns() → pick IDs → get_run_details()). It also routes AI insights retrieval to get_ai_insights for polling and the optimize_swarm prompt for swarm analysis, with no ambiguity about which tool to use when.

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