Skip to main content
Glama

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

learn_conventions

Analyze a TouchDesigner subtree to infer naming, color, topology, and parameter conventions, then save them to an Obsidian vault for consistent project styling.

Instructions

Read a TouchDesigner subtree under scope_path without changing TD, infer naming/colour/topology/parameter conventions, and write the result to the configured Obsidian vault. This is read-only on the TD side but mutates vault files: by default it writes Memory/conventions.md and may merge confident naming/layout signals into Memory/style.md. Set dry_run=true to inspect the extract without disk writes. Use learn_from_my_corpus when the source is already in the vault and load_session_profile when you only need to consume cached preferences. Requires TDMCP_VAULT_PATH and returns sampled conventions plus write flags.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runNoIf true, return the extracted conventions but do NOT write the vault note.
observeNoWhich convention families to extract.
max_nodesNoCap on nodes walked (BFS, depth-unlimited until cap).
scope_pathNoRoot COMP whose subtree is sampled. Defaults to /project1./project1
min_supportNoA pattern must appear at least this many times to be recorded.
also_patch_style_memoryNoIf a confident naming/layout signal is found, also merge it into Memory/style.md.
Behavior5/5

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

The description goes beyond the annotations by clarifying the dual-side effect: 'read-only on the TD side but mutates vault files', names default writes (Memory/conventions.md and possible Memory/style.md merge), and explains dry_run behavior. This is substantial behavioral context not available from annotations alone.

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?

The description is compact but information-dense; every sentence adds value (purpose, side effects, dry_run, alternatives, requirements/returns). It is front-loaded with the core function and avoids redundancy.

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

Completeness5/5

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

For a tool with six parameters and no output schema, the description covers purpose, side effects, alternatives, environmental prerequisite, and a summary of returns ('sampled conventions plus write flags'). This is sufficient for correct selection and invocation.

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 coverage is 100%, so the baseline is 3. The description adds meaningful context beyond the schema by mentioning the TDMCP_VAULT_PATH requirement and how dry_run affects writes, enriching parameter understanding without duplicating schema details.

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 uses a specific verb ('Read a TouchDesigner subtree... infer naming/colour/topology/parameter conventions, and write the result') and clearly identifies the resource and output. It distinguishes itself from sibling tools by naming alternatives (learn_from_my_corpus, load_session_profile), leaving no ambiguity about its scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance is given: 'Use learn_from_my_corpus when the source is already in the vault and load_session_profile when you only need to consume cached preferences.' The dry_run flag is also presented as an inspection option, making the tool's usage contexts clear.

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/lucasmaher-hash/touch-designer-mcp'

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