Skip to main content
Glama
GaNotchVFX

touchbridge

by GaNotchVFX
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

bridge_send

Send raw opcodes and payloads to TouchDesigner's bridge for live node, parameter, and timeline control. Safe mode permits only non-destructive router methods.

Instructions

Raw bridge send: op + payload. In safe mode only catalogued non-destructive router methods pass; the raw python/eval opcodes need --allow-destructive.

op (<class 'str'>): Bridge opcode (eval, python, ...).

payload (dict[str, typing.Any]): Payload dict.

detail (str | None): full (default) | summary (long lists cut to 25 + count) | minimal (top-level scalars only).

response_format (str | None): yaml (default, token-cheap) | json.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opYes
detailNo
payloadNo
response_formatNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.4.0
    • addedInput schema / properties / detail
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Detail"
+}
    • addedInput schema / properties / response_format
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Response Format"
+}
  2. First observedv0.2.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and covers the key risk profile: it is a raw opcode sender (eval/python imply arbitrary execution), safe mode filters non-catalogued operations, and destructive ops need --allow-destructive. It also reveals that yaml is the "token-cheap" default. It omits error behavior for rejected opcodes, but the core safety and efficiency traits are disclosed.

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?

The description is front-loaded with purpose and the safety caveat, followed by a compact per-line parameter block where each entry is dense and useful. Minor redundancy: it repeats Python type annotations (e.g., "(<class 'str'>)") that already exist in the input schema, adding slight noise, but nothing else is wasted.

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 4-parameter tool with no output schema and no annotations, it covers purpose, the safe-mode/destructive context, and every parameter's semantics including response shaping. The main gap is return/error behavior — e.g., what an agent sees when a disallowed opcode is rejected in safe mode — but the essentials for correct invocation are all present.

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

Parameters5/5

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

Schema description coverage is 0%, so the description is the sole documentation for all four parameters, and it fully compensates: op is explained as an opcode with examples, payload as an arbitrary dict, detail enumerates full/summary/minimal including the list cutoff behavior ("long lists cut to 25 + count"), and response_format gives yaml/json with defaults. This adds meaning far beyond the bare schema.

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 opening line "Raw bridge send: op + payload" states a specific verb, resource, and the escape-hatch nature of the tool. The safe-mode sentence explicitly contrasts it with catalogued non-destructive router methods, which maps directly to the sibling bridge_router_call and lets an agent distinguish the raw opcode path without opening the schema.

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?

"In safe mode only catalogued non-destructive router methods pass; the raw python/eval opcodes need --allow-destructive" gives clear context about when this raw tool will actually work and flags that the destructive opcodes require a server-side flag. It stops short of explicitly naming bridge_router_call as the alternative for safe operations, so the when-not guidance is strong but implied rather than stated.

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