Skip to main content
Glama
bedrock-map-builder-mcp

bedrock-map-builder-mcp

by xRookieFight

plan_run

Runs a plan's pending steps in order, retrying failures and resuming interrupted edits; stops at the first error unless continue_on_error is set, or after max_steps to report progress.

Instructions

Run a plan's pending steps in order (failed steps are retried). Interrupted world edits resume from the tiles they finished. Stops at the first error unless continue_on_error, and after max_steps so long plans can report progress.

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": {
      "plan": "<plan>"
    },
    "name": "plan_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
planYes
max_stepsNo
continue_on_errorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden of describing behavior, and it does so well. It states that failed steps are retried, that interrupted world edits resume from the tiles already finished, that execution halts at the first error unless continue_on_error is set, and that it stops after max_steps. It leaves open how destructive the run is, what happens to remaining steps after a halt, and what the response looks like, but its behavioral disclosure is well above baseline.

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?

It is three dense sentences with no filler, and the core action is front-loaded before the caveats. The parenthetical resumption note is slightly compressed but still readable.

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?

For a mutation tool with no annotations and no output schema, the description covers the key behaviors an agent needs in order to invoke it safely: retry, resumption, error-stop semantics, and step bounding. The remaining gaps that keep it from being complete are how the plan is identified, whether edits are reversible, and what progress information is returned.

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 0%, so the description must explain the parameters, and it explains continue_on_error and max_steps through their runtime effects. However, it never describes the required plan parameter (ID vs. name vs. path), and it does not connect the max_steps default of 50 or the maximum of 500 to the described behavior, leaving a real gap.

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?

The description leads with a specific verb and resource: 'Run a plan's pending steps in order.' That is enough to distinguish it from the sibling plan-management tools (plan_create, plan_edit, plan_list, plan_show), which manipulate plan definitions rather than executing them.

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?

The description makes it clear that the tool executes a plan, and the parenthetical about retrying failed steps implies that the tool is meant for resuming or continuing work. However, it never says when to use this tool instead of run_commands or plan_show, nor does it state prerequisites such as whether the plan must exist or be opened first.

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