FoxPlug

check_drift

Read-only

Check whether a project's recent work still matches its current plan. FoxPlug compares the plan you set (via set_plan) against the work recorded since, and returns an alignment verdict with any divergences — work that is off-plan, or plan items nothing has moved toward. Read-only judgment; it never posts anything. Free.

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": {
      "project": "<project>"
    },
    "name": "check_drift"
  }
}

Input Schema

Name	Required	Description	Default
`project`	Yes	The project this work belongs to — a FoxPlug project name, domain, or repo (e.g. 'foxplug', 'foxplug.com', or 'owner/lcncagents'). Matched case-insensitively against your own FoxPlug projects and any repo/deploy routes. If it can't be resolved, nothing is written (not dropped) and the reply lists your project names so you can retry with an exact one.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces rather than contradicts them ('Read-only judgment; it never posts anything'). It adds real context the annotations cannot: what the verdict contains, both divergence directions (off-plan work and unmoved plan items), and that calls are free, which matters for a tool an agent may call repeatedly.

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 the purpose, followed by mechanism, output, and cost guarantees — a sensible order with little waste. The divergence clause is slightly verbose, but it is informative rather than filler.

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, and the description compensates by describing the return value (verdict plus divergences). Combined with a fully documented single required parameter and annotations covering the safety profile, an agent has everything needed to decide and call correctly.

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% and the single 'project' parameter is already documented with accepted identifier forms and the failed-resolution behavior, so the description adds nothing about parameters. Baseline 3 applies when the schema carries the parameter semantics fully.

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 ('Check whether a project's recent work still matches its current plan') and names the producing counterpart ('the plan you set via set_plan'), so the agent can distinguish it from plan-setting siblings. It also names the output shape ('alignment verdict with any divergences'), which is more than most definitions give.

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?

Implies the trigger condition clearly — use it after work has been recorded, to test drift against a plan created via set_plan. It does not explicitly exclude or contrast with get_plan_status, so the boundary with that sibling is left for the agent to infer.

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

All FoxPlug tools Inspect

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

Need Help?