Skip to main content
Glama

Auto-repair loop (bounded)

auto_repair_loop

Scans a TouchDesigner subtree for cook errors, routes each cluster to the appropriate fix, re-checks, and iterates until clean or stalled. Dry-run by default for planning.

Instructions

Driver: scan a subtree for cook errors, cluster them, route each cluster to the right fix (calls repair_network for structural/expression/flag issues; surfaces fix_shader / fix_reactivity as prompt hand-offs the agent must execute next turn), re-check, and iterate until clean, no-progress (stalled), or max_iterations (exhausted). Dry-run by default — one planning iteration, no writes. The loop CANNOT fix shaders or dead reactivity itself; it points the agent at them via recommended_prompts. Returns {status, iterations[], errors_before, errors_after, remaining[], recommended_prompts[], warnings}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNoRoot of the subtree to scan + repair./project1
max_iterationsNoHard cap on outer iterations — each iteration = one scan + one route + one apply.
dry_runNoWhen true (default), PLAN routes only (no writes). Propagated to repair_network; the loop runs exactly one iteration in dry-run mode.
allowed_fixersNoSubset of fixers the loop may route to. Drop 'repair_network' to make the loop advisory only (prompts + remaining, no writes).
min_progressNoConvergence threshold — if an iteration clears fewer than this many errors, the loop stops (stalled).
include_warningsNoWhen true, treat 'warning' severity errors as in-scope. Default ignores warnings (no-op until the bridge surfaces severity).
Behavior5/5

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

Annotations (readOnlyHint=false, destructiveHint=false) are consistent with the description. The description adds rich behavioral context: iterative execution, dry-run mode, convergence detection, and what the loop cannot do. It also details the return object structure, enhancing transparency beyond annotations.

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 concise, single paragraph, front-loaded with key actions: scan, cluster, route, re-check, iterate. Every sentence adds value without redundancy. It efficiently conveys the tool's purpose, behavior, and limitations.

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?

Given no output schema, the description fully details return values: status, iterations[], errors_before, errors_after, remaining[], recommended_prompts[], warnings. It also covers parameter interactions (dry_run, allowed_fixers) and edge cases (stalled, exhausted). The description is comprehensive for an iterative repair tool.

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 100%, so baseline is 3. The description adds value by explaining behavior beyond schema, e.g., dry_run implies one iteration, allowed_fixers can be dropped for advisory mode. This extra context justifies a score of 4.

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 clearly states the tool's purpose: scan a subtree for cook errors, cluster them, route to fixers, re-check, and iterate until clean, stalled, or exhausted. It uses specific verbs and resources, and distinguishes from sibling tools by naming specific fixers like repair_network, fix_shader, fix_reactivity.

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?

The description explicitly states default dry-run mode (planning only, no writes), the loop's limitation (cannot fix shaders or dead reactivity itself, points agent to recommended_prompts), and the convergence threshold via min_progress parameter. It also explains the allowed_fixers parameter behavior, providing clear guidance on when to use and alternatives.

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