Skip to main content
Glama
Sign In

LexQ

by io.lexq
OverviewDiscussionsAdmin

Replay a Decision

lexq_replay_decision
Read-only

Re-evaluate a past execution (traceId) against a candidate version and return the decision diff (decisionChanged, effect changes, fired rules) plus a determinism verdict. Synchronous. Not billed and not counted toward the plan's usage. Dry runs, dry run compares, and single-decision replays share two limits for each organization: 60 evaluations per minute and 1000 per UTC day; a compare counts as two. Past the per-minute limit, a call fails with 429 (C-007); wait a minute before trying again. Past the daily limit, a call fails with 429 (AN-041) until 00:00 UTC. A call refused by the per-minute limit does not count toward the daily limit. A replay sends no webhook, notification, or event: rule actions produce no outward effects.

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": {
      "traceId": "<traceId>",
      "candidateVersionId": "<candidateVersionId>"
    },
    "name": "lexq_replay_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
traceIdYesTrace ID of the past execution to replay
candidateVersionIdYesVersion to re-evaluate against

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the annotations, which only declare a safe read-only, closed-world operation. The description adds billing exemption, quota mechanics (60/min, 1000/day UTC, compare counts as two), distinct 429 codes C-007 and AN-041 with wait semantics, and the guarantee that no webhook, notification, or event is emitted — exactly the behavioral context an agent needs. No contradiction with readOnlyHint=true or destructiveHint=false.

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?

Purpose and return shape are front-loaded in the first sentence, with operational constraints after. The quota/429 passage is dense and slightly repetitive ('per-minute limit' appears three times), but each clause conveys actionable error-handling behavior.

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?

With no output schema, the description compensates by enumerating the returned diff fields and the determinism verdict. Combined with its coverage of timing, cost, quotas, and side-effect absence, 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.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema already describes both fields ('Trace ID of the past execution to replay', 'Version to re-evaluate against'). The description adds no format, sourcing, or validation detail beyond that, so the baseline 3 applies.

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 — re-evaluate a past execution identified by traceId against a candidate version — and even names the returned payload (decisionChanged, effect changes, fired rules, determinism verdict). It is clearly distinct from lexq_dry_run (no trace) and lexq_replay_start (batch/async, implied by 'Synchronous'), but it never explicitly names those siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operating context: it is synchronous, free of billing, and shares the dry-run/compare quota — enough for an agent to pick it for a single-trace what-if check. It stops short of an explicit when-not clause pointing at lexq_replay_start or lexq_dry_run_compare as the alternative.

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

All LexQ toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources