Skip to main content
Glama
Sign In
shapeyourphone

shapeyourphone

by rachitkj
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

apply_plan

Execute a saved debloat or clone plan on an Android phone, previewing changes until the owner approves and logging every change with undo.

Instructions

Apply a plan file (from plan_debloat or clone). Every change is logged with its undo.

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_path": "<plan_path>"
    },
    "name": "apply_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoadb serial, only needed when several phones are connected
plan_pathYes
owner_approvedNotrue only after the phone's owner saw the preview and agreed. Omit to get a preview.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With readOnlyHint=false and destructiveHint=false already declared, the description adds a genuinely useful behavioral guarantee: every change is logged and carries an undo. However, it omits the most consequential behavioral trait — that omitting owner_approved yields a dry-run preview rather than applying anything — and does not say whether applying is idempotent or what happens to device state that the plan does not cover.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and its input source, followed by the safety guarantee. Nothing is padded or redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a state-changing 3-parameter tool with no output schema, the definition is minimal: it never says the default is a preview, does not describe what is returned or how to inspect results, and does not indicate requirements like an explicit owner approval. An agent could invoke it expecting immediate changes and be surprised by the preview behavior.

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 67%, with device and owner_approved documented in-schema and plan_path undocumented. The description compensates slightly by giving plan_path provenance (from plan_debloat or clone), which is real added meaning, but says nothing about the semantics of applying or about the owner_approved confirmation gate. Baseline 3 is appropriate.

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?

The description states a specific verb and resource ('Apply a plan file') and names the two sibling tools that produce such a plan (plan_debloat, clone), which lets an agent distinguish it from the generator tools. It stops short of describing what applying actually does to the device, so it is clear but not fully self-contained.

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?

Usage is only implied: the mention of plan_debloat/clone signals this is the execution step after planning, but there is no explicit when-to-use statement, no mention of the preview-first workflow, and no pointer to undo/restore_everything as the recovery path. The key gate ('Omit to get a preview') lives only in the schema, not in the description.

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

Deploy Server

Other Tools