Checkbox

Get the compliance plan (ordered tasks)

get_compliance_plan

Read-onlyIdempotent

The main tool after setup. Returns the ordered tasks that make the site pass the automatic-renewal checks, recomputed from the latest observations. Each task has: requirement + legal citation, why (what Checkbox observed), where (file / component / URL / CSS selector / Stripe object), change (exact unified-diff template, copy text or Stripe params), and verify (how to check). Plan status: action_required (apply open tasks), verifying (waiting for confirming observations), compliant (done: the checks pass — "pending_live_check" tasks count as passing: they complete on their own or with a proof run), blocked (only human questions — "Your call" — left). Tasks are tagged tier required / recommended / extra. Only required tasks matter for compliance; recommended and extra tasks are optional suggestions (mention them once, do not push them). Loop: apply the first open required task in the code → verify_task → get_compliance_plan → … until the checks pass (status compliant). Tasks with status "manual" carry a question with a recommended answer: ask the HUMAN, then answer_task. Never invent answers.

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": "get_compliance_plan"
  }
}

Input Schema

Name	Required	Description	Default
`site`	No	Site id (site_…). Optional when the account has exactly one site in this mode; list_sites shows them.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses that results are recomputed from latest observations, defines all four plan statuses, and clarifies the non-obvious rule that pending_live_check tasks count as passing. This is the kind of nuance an agent cannot infer from annotations or schema.

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 purpose and return contract, then statuses, tiers, and the loop; every block carries information an agent needs. It is dense for a single-parameter read tool and mixes return schema with workflow policy, so it falls just short of ideal tightness.

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?

No output schema exists, so the description must carry the return contract — and it does, enumerating the per-task fields (requirement, why, where, change, verify), status values, and tier tags. Nothing needed to call or interpret the tool is missing.

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?

Only one parameter and the schema already documents it fully (site id, optional when the account has a single site, with a pointer to list_sites). The description adds no additional meaning about the site parameter, so the high schema coverage makes the baseline 3 appropriate.

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 ('Returns the ordered tasks that make the site pass the automatic-renewal checks') plus the recomputation source ('from the latest observations'), which distinguishes it from get_task, get_verification and list_findings. The 'main tool after setup' framing tells the agent where it sits in the workflow.

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

Usage Guidelines5/5

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

Explicit routing: apply first open required task → verify_task → get_compliance_plan loop, plus a named alternative for a specific condition (manual-status tasks → ask the HUMAN → answer_task). It also states what to deprioritize ('mention them once, do not push them') and prohibits guessing answers.

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

All Checkbox tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.