Skip to main content
Glama

acceptance_criteria_validator

Read-onlyIdempotent

QA advisor: validate acceptance criteria quality. POST a list of AC (or a story) and get per-AC problems (vague/untestable, non-atomic, no observable outcome) + a missing-coverage flag if there is no failure-path AC, plus a 0-100 score and pass/needs_work verdict. Tells you exactly what to fix. Deterministic, no LLM.

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": "acceptance_criteria_validator"
  }
}

Input Schema

NameRequiredDescriptionDefault
storyNoAlternative: full story text; the AC lines are extracted from it.
strictnessNoDefault "normal". "strict" also flags subjective wording in measurable criteria.
acceptance_criteriaNoThe criteria, one string each (max 50). Wins over story.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / acceptance_criteria / description
      Added value: +"The criteria, one string each (max 50). Wins over story."
    • addedInput schema / properties / acceptance_criteria / items / maxLength
      Added value: +2000
    • addedInput schema / properties / acceptance_criteria / maxItems
      Added value: +50
    • addedInput schema / properties / story / description
      Added value: +"Alternative: full story text; the AC lines are extracted from it."
    • addedInput schema / properties / story / maxLength
      Added value: +16000
    • addedInput schema / properties / strictness / description
      Added value: +"Default \"normal\". \"strict\" also flags subjective wording in measurable criteria."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real behavioral value beyond them: it is deterministic with no LLM, and it discloses the shape of the response (per-criterion findings, coverage flag, numeric score, verdict) plus that it is prescriptive ('tells you exactly what to fix'). It does not mention whether calls consume credits or any rate limits, which is a minor gap given quota-adjacent siblings like buy_credits and rate_call.

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?

Two dense sentences, front-loaded with purpose and then results, with no filler. The only cost is mild compression ('POST a list of AC') that reads slightly jargon-like, but nothing is wasted.

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 correctly takes on the job of describing the return payload and verdict scale, which it does well for a 3-parameter read-only validator. It stops short of covering behavior on empty/ambiguous input or how the score maps to pass versus needs_work thresholds.

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%, including the precedence rule ('Wins over story') and strictness semantics, so the schema carries the parameter burden. The description adds no format or edge-case detail beyond what is already documented, so the baseline 3 applies.

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 ('validate acceptance criteria quality') and enumerates the exact outputs: per-AC problems (vague/untestable, non-atomic, no observable outcome), a missing-coverage flag for absent failure-path AC, a 0-100 score, and a pass/needs_work verdict. An agent can distinguish this from generic siblings like story_lint or ticket_lint without opening the schema.

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?

'POST a list of AC (or a story)' implies the calling context and makes the two input modes clear, but there is no explicit when-to-use/when-not framing and no named alternative (e.g., story_lint for whole-story review). Usage is inferable rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.