Skip to main content
Glama

Learn the artist's house conventions from a live TD subtree

learn_conventions

Analyze a TouchDesigner subtree to extract naming, color, topology, and parameter conventions. Saves results to a vault note for consistent project style, without modifying the scene.

Instructions

Walks a TouchDesigner subtree under scope_path (read-only), extracts naming/colour/topology/parameter conventions, and writes the findings to the shared Memory/conventions.md note (and, when confident, merges naming/layout into Memory/style.md). Pure observation: no TD mutations. Requires TDMCP_VAULT_PATH.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scope_pathNoRoot COMP whose subtree is sampled. Defaults to /project1./project1
observeNoWhich convention families to extract.
max_nodesNoCap on nodes walked (BFS, depth-unlimited until cap).
min_supportNoA pattern must appear at least this many times to be recorded.
dry_runNoIf true, return the extracted conventions but do NOT write the vault note.
also_patch_style_memoryNoIf a confident naming/layout signal is found, also merge it into Memory/style.md.
Behavior1/5

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

Description claims 'Pure observation: no TD mutations' but annotations set readOnlyHint=false, a direct contradiction. The description also discloses writing to memory files, which are side effects, but the contradiction with annotations overrides any positive transparency.

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?

Description is a single paragraph, front-loads purpose, and includes key constraints. Could be slightly more concise but no unnecessary words.

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?

Covers main function and side effects (writing notes), but lacks details on return format, failure modes (e.g., missing vault path), and how confident signals are determined. More completion needed for a 6-param tool with no output schema.

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 covers 100% of parameters, so baseline 3. Description does not add meaningful details beyond the schema; it only mentions scope_path and observe in passing. No extra context for values or behavior.

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?

Description clearly states verb (walks/extracts/writes), specific resource (TouchDesigner subtree under scope_path), and outcome (conventions to Memory/conventions.md). Distinguishes from siblings as a convention-learning tool with no TD mutations.

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?

Implies usage for learning conventions from a live TD subtree and notes it is read-only and requires vault path, but lacks explicit when-to-use vs alternatives or when-not-to-use guidance. No mention of comparison with analyze_project or style_memory.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Pantani/tdmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server