comfy-draftsman

Overview Schema Source Related Servers Discussions Admin

record_learning

Persist researched ComfyUI settings and verified source URLs so future workflow sessions reuse learned defaults and auto-recognize new model families.

Instructions

Persist researched settings so FUTURE sessions start smarter. updates uses the guidance shape, e.g. {"sampling": {"cfg": {"default": 3.5}}} or {"techniques": {"face_detailer": {"denoise": 0.4}}}. source = URL/model page. Any family name works; for a NEW family also include a "detect" block so it's auto-recognized next session: {"detect": {"checkpoint_patterns": ["mymodel"]}, "loader": "unet_clip_vae"}.

A "sources" list teaches organize_workflow's Models note where to download each file - it never invents a URL, so this is the only way one appears: {"sources": [{"match": ["mymodel_v1.safetensors"], "what": "checkpoint", "url": "https://..."}]}. Verify the URL resolves first.

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": {
      "family": "<family>"
    },
    "name": "record_learning"
  }
}

Input Schema

Name	Required	Description	Default
`family`	Yes
`source`	No
`updates`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.25.0Oct 24, 2026
- addedInput schema / properties / source / default
```
Added value: +""
```
- addedInput schema / properties / updates / default
```
Added value: +{}
```
- changedInput schema / required
```
Previous value: -[
-  "family",
-  "updates",
-  "source"
-]New value: +[
+  "family"
+]
```
Changed4 schema fields changedv0.15.1Aug 23, 2026
- removedInput schema / properties / family / title
```
Removed value: -"Family"
```
- removedInput schema / properties / source / title
```
Removed value: -"Source"
```
- removedInput schema / properties / updates / title
```
Removed value: -"Updates"
```
- removedInput schema / title
```
Removed value: -"record_learningArguments"
```
First observedv0.2.0Jul 7, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already disclose this is a non-readOnly, non-destructive, closed-world write. The description adds real behavioral context beyond that: it is the only path by which a URL appears in organize_workflow's note ('it never invents a URL'), and it warns to verify the URL resolves. It still doesn't describe storage scope or persistence lifetime, but the added context is substantial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded with purpose first, and the examples earn their space, but the prose is dense with awkward line breaks and multiple nested JSON snippets that could be tightened. It borders on longer than necessary for three parameters.

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?

An output schema exists so return values need no explanation, and all three parameters are meaningfully described despite zero schema coverage. The detect-block and sources-list mechanics make the write operation actionable; only storage/persistence semantics remain lightly specified.

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 0%, so the description must carry the burden, and it largely does: 'updates' is explained with concrete guidance-shape examples, 'source' is defined as URL/model page, and 'family' semantics plus the optional 'detect' block are spelled out. Only minor details (e.g., allowed loader values, matching semantics) are left implicit.

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?

The description states a specific verb and effect: persist researched settings so future sessions start smarter, which is distinct from read-only siblings like get_model_guidance. It does not explicitly contrast itself with those siblings, but it references organize_workflow's Models note, giving some relational clarity.

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?

Usage is implied through conditional guidance ('for a NEW family also include a detect block') and a caveat about URL verification, but there is no explicit when-to-use vs when-not-to-use statement or named alternative. An agent can infer the post-research context but must reason it out.

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