brain-core

Overview Schema Source Related Servers Discussions Admin

brain_distill

Idempotent

Captures web pages, GitHub READMEs, YouTube subtitles, PDFs, local files, or pasted text into a dated, provenance-tracked markdown file in the immutable raw/ folder for later distillation.

Instructions

Capture an external source into the agent's immutable raw/ folder as a dated markdown file with provenance: source, title, author, published, sha256, word count. This is step 1 of /distill; compiling the knowledge page from the raw file is your job afterwards.

    Use it for a web page (defuddle with a stdlib fallback), a GitHub repo README, YouTube
    subtitles via yt-dlp, a PDF saved as bytes, a local file, or pasted text. Not for short
    facts (brain_remember).

    Fetches over the network for URLs. The same source or body a second time returns
    `status: exists` and writes nothing. A `note` flags a thin capture (JS-only or paywalled
    page) so you can read it in a browser and call again with `text`.

Input Schema

Name	Required	Description
`text`	No	The body itself, when you already have it; skips fetching.
`title`	No	Override the detected title.
`author`	No	Override the detected author.
`source`	Yes	A URL (web page, GitHub repo, YouTube video, PDF), a local file path, or a short name for pasted `text`.
`published`	No	Publication date YYYY-MM-DD, if known.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.2.6Nov 2, 2026

addedInput schema / properties / author / description
```
Added value: +"Override the detected author."
```

addedInput schema / properties / published / description

Added value: +"Publication date YYYY-MM-DD, if known."

addedInput schema / properties / source / description

Added value: +"A URL (web page, GitHub repo, YouTube video, PDF), a local file path, or a short name for pasted `text`."

addedInput schema / properties / text / description

Added value: +"The body itself, when you already have it; skips fetching."

addedInput schema / properties / title / description
```
Added value: +"Override the detected title."
```

First observedv0.1.0Nov 2, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses network fetching for URLs, that raw/ is immutable, that a repeat submission is idempotent and returns 'status: exists' without writing, and that a `note` flags thin JS-only or paywalled captures with a recommended retry path. Those are exactly the behavioral traits (side effects, retry semantics, partial-failure signaling) annotations cannot convey.

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?

Front-loaded with the core action and scope in the first sentence, then capability, then exclusion, then behavioral caveats — a sensible order with no filler. It is on the dense side for a description, but nearly every clause carries decision-relevant information.

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?

An output schema exists, so return shapes need not be spelled out, and the description still covers the one return value an agent must branch on ('status: exists'). For a 5-param write tool with openWorld behavior, nothing needed to call it correctly is missing.

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 field meanings are already documented; the description still adds real semantics by explaining the interplay between `source` and `text` ('call again with `text`' when a capture is thin) and that supplying the body skips fetching. That is useful beyond the per-field descriptions, though it does not cover `published`/`author` overrides explicitly.

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?

States a specific verb and destination ('Capture an external source into the agent's immutable raw/ folder as a dated markdown file') plus the provenance fields written. It also explicitly separates itself from brain_remember for short facts, so an agent can distinguish it from siblings without opening any schema.

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?

Enumerates the supported input kinds (web page, GitHub README, YouTube subtitles, PDF bytes, local file, pasted text) and gives an explicit exclusion ('Not for short facts (brain_remember)'). It also positions the tool as step 1 of /distill and states what the caller must do afterward, which removes ambiguity about the follow-up workflow.

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

Deploy Server