Skip to main content
Glama
Sign In
Swipium

Swipium

by GeroPalombo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Generate persistent suite cases from the app

qa_suite_generate

Generate test cases from recorded QA sessions and merge them into a durable repository suite, updating existing cases on re-runs without duplicates while reporting coverage gaps.

Instructions

Generate cases from this session (recorded actions, outcomes, exploration coverage) and merge them into the durable repo suite .swipium/test-suite.json (re-runs update, no duplicates). Returns cases, skipped features, and coverage gaps. Per-run assets: qa_generate.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "qa_suite_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
featureNoFunctionality label (default: the recorded flow name).
sessionIdNo
creativityNoHow far beyond the happy path (default standard).
projectRootNo
creativityLevelNoDeprecated alias of creativity.
includeManualOnlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only say it writes (readOnlyHint=false) without destroying (destructiveHint=false); the description adds materially: the exact durable file written, that re-runs update rather than duplicate, and what is returned (cases, skipped features, coverage gaps). Merge/no-duplicate semantics are the key operational fact an agent needs and are not derivable from annotations.

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?

Three front-loaded sentences with zero filler; the write target and merge behavior come before the return-value summary. The trailing 'Per-run assets: qa_generate' is tersely worded jargon but still earns its place as a routing hint.

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 supplies the return shape (cases, skipped features, coverage gaps) and the persistence target, which is enough for an agent to call it correctly. It omits failure modes (e.g., what happens with no recorded session) and does not clarify includeManualOnly's effect on the merge.

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 coverage is 50%, and the description compensates only partially: 'from this session' implies sessionId, and 'coverage' loosely relates to creativity, but includeManualOnly, projectRoot, and the deprecated creativityLevel alias are left entirely to the schema. Acceptable but not compensating for the coverage gap.

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?

States a specific verb and resource ('Generate cases from this session') plus a concrete destination ('merge them into the durable repo suite .swipium/test-suite.json'). It also distinguishes itself from the ephemeral sibling by noting 'Per-run assets: qa_generate,' though it does not contrast itself with qa_suite_update.

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?

Usage is implied by 'from this session (recorded actions, outcomes, exploration coverage)' — the agent can infer a prior recorded session is required. The 'Per-run assets: qa_generate' line hints at an alternative, but there is no explicit when-to-use/when-not or prerequisite statement, and no guidance on choosing between this and qa_suite_update.

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

Deploy Server

Other Tools