Skip to main content
Glama

live_edit

Destructive

Modify the current owned ISIS sheet in the same document using native add, transform, set, connect, and targeted delete operations; requires a stopped simulation and valid live token.

Instructions

Edit the CURRENT owned ISIS sheet in the same PID/document using native functions. Stopped simulation and current live_read token required. Operations: add, transform, set, connect. Deletion is a separate batch: {op:delete,ref,delete_connected_wires:false} permits direct attached component wires only when true; {op:delete_wire,wire_address} removes one exact wire including a branch; {op:delete_junction,junction_address,connected_wire_addresses:[all exact incident addresses]} removes a DOT and explicitly listed incident wires, never a whole net. Non-target geometry/labels are compared; native selections/tags are rejected. NOT atomic; partial/unconfirmed may have applied. Save/reopen for disk validation.

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": {
      "session": "<session>",
      "expected_token": "<expected_token>",
      "operations": "<operations>"
    },
    "name": "live_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionYes
operationsYes
expected_tokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the destructiveHint/readOnlyHint annotations: warns the operation is NOT atomic, that partial or unconfirmed changes may already have applied, that non-target geometry and labels are compared, that native selections/tags are rejected, and that save/reopen is needed for disk validation. This is exactly the operational context an agent needs before a destructive edit.

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-loads scope and preconditions, then groups operation semantics including the deletion variants. Dense but each clause carries information; the deletion sentences are long and could be formatted more scannably.

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 destructive, non-atomic mutation tool with no output schema, the definition covers preconditions, operation grammar, deletion constraints, and validation advice. Return/result reporting is only hinted at via 'partial/unconfirmed may have applied', leaving result interpretation slightly underspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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

Schema description coverage is 0%, so the description must carry the load: it defines expected_token as the current live_read token and describes the operations array in detail, including delete, delete_wire and delete_junction shapes with their required fields. Session is only implied (PID/document), which is the remaining gap.

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?

Names a specific verb and resource ('Edit the CURRENT owned ISIS sheet in the same PID/document using native functions') and constrains scope to the current owned document, which separates it from cross-document or native_* tools. It stops short of explicitly naming a sibling it is not, so it is clear but not fully differentiated.

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?

States preconditions clearly (stopped simulation, current live_read token) and marks deletion as a separate batch with its own op shapes, which effectively tells the agent when to use this tool versus a delete flow. No explicit 'use X instead' alternatives are given.

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