Skip to main content
Glama

sn_atf_results

Read-onlyIdempotent

Retrieve paginated ATF suite results, read full step summaries or output in chunks, and inspect cached run history or comparisons without extra network calls.

Instructions

Get paginated ATF suite results, retrieve complete step summary/output in chunks, or inspect cached history/comparisons. History and compare need no ServiceNow network requests. Results may include untrusted failure text.

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": {
      "action": "<action>",
      "profile": "<profile>"
    },
    "name": "sn_atf_results"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum cached runs to display in history (default 10)
actionYesFetch paginated results, retrieve complete step text, read cached history, or compare cached runs
profileYesConfigured ServiceNow profile name (required; no default fallback).
result_idNoCI/CD result ID for get, or current cached run ID for compare
progress_idNoCI/CD progress ID for get while awaiting a result
test_sys_idNoTest ID for history across cached suites
tests_limitNoTest summaries per page (default 200)
output_fieldNoStep text field to retrieve (default summary)
output_limitNoStep-text chunk length (default 4000 characters)
suite_sys_idNoSuite ID required for history or compare unless selecting test history
tests_offsetNoTest-summary page offset for get (default 0)
output_offsetNoCharacter offset for the next step-text chunk
failures_limitNoFailure details per page (default 10)
step_result_idNoStep result ID for action=step; returned with failures
failures_offsetNoFailure-detail page offset for get (default 0)
previous_result_idNoPrevious cached run ID for compare
regression_percentNoDuration regression threshold, percent (default 20)

Output Schema

NameRequiredDescriptionDefault
dataYes
profileYesConfigured ServiceNow profile name (required; no default fallback).
metadataYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.2.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds value on top: it discloses that history and compare are served from cache with no ServiceNow network traffic, and that results may contain untrusted failure text, which is a genuine safety caveat for downstream handling. It does not describe pagination termination or rate/error behavior, but the added context is substantive rather than repetitive.

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?

A single sentence, front-loaded with the primary verb phrase, with three parallel clauses covering the action modes and a trailing safety note. Nothing is wasted, though the compressed fragment 'Results may include untrusted failure text.' is terse enough that its implication (sanitize before rendering) is left implicit.

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 17 parameters the schema does the heavy lifting, an output schema exists so return values need no explanation, and the description still covers the four action modes, the cache/network distinction, and the untrusted-content caveat. What remains missing is minor: no indication of pagination completion signals or how the required profile relates to configured ServiceNow profiles.

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 100%, so every one of the 17 parameters is already documented in the input schema, including chunking limits and ID patterns. The description adds only the high-level action framing, which the action enum already provides, and nothing about the interplay between output_offset/output_limit or suite_sys_id vs test_sys_id. Baseline 3 is appropriate when the schema carries the parameter burden.

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 uses concrete verbs tied to resources: paginated ATF suite results, chunked step summary/output, cached history and comparisons. Those four clauses map directly onto the action enum, so an agent can tell which mode does what. It stops short of naming a sibling (e.g. sn_atf_run) to distinguish launching vs. reading results, so it is clear but not fully differentiated.

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?

Per-goal routing is implied rather than stated: 'retrieve complete step summary/output in chunks' points to action=step, 'inspect cached history/comparisons' points to history/compare. The note that history and compare need no ServiceNow network requests is useful context for choosing an offline path. However, there is no explicit when-not guidance and no named alternative for launching or re-running ATF suites among the siblings.

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