Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_brain_index

Indexes module rows into a unified semantic space and refreshes only rows changed since the last run. Use the optional kinds parameter to backfill one data source at a time.

Instructions

Index (or incrementally refresh) module rows into the unified semantic space. Only rows changed since the last run are touched (watermark). Pass kinds to backfill one module at a time. Embeds row text, so run it deliberately when the embeddings backend is healthy.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "kernel_brain_index"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindsNoRestrict indexing to these kinds. Omit to index all sources.

Output Schema

NameRequiredDescriptionDefault
indexedYes
removedYes
per_kindYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses the watermark-based incremental behavior (only changed rows touched), the embedding cost/side effect, and an external dependency on backend health. It stops short of stating permission requirements, concurrency safety, or idempotency guarantees.

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?

Three short sentences, each front-loaded with its most important clause: what it does, how incrementality works, how to scope with `kinds`, and the operational caveat. No restated name, no filler.

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 the description covers the behavioral essentials for a single-optional-parameter mutation. It could be stronger by noting valid `kinds` values or whether repeated runs are safe, but nothing critical is missing for correct 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, but the description adds real meaning beyond the schema by explaining the backfill workflow implied by `kinds`. The schema already covers the omit-to-index-all behavior, so the gain is modest rather than large.

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?

States a specific verb and resource — indexing module rows into a 'unified semantic space' — plus the incremental variant. The name and description together make the operation unambiguous. It does not explicitly contrast itself with the read-side siblings (kernel_brain_recall/ask/stats), so an agent must infer that this is the write/build counterpart.

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

Usage Guidelines4/5

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

Gives concrete usage context: incremental refresh by default, use `kinds` to backfill one module at a time, and a precondition that the embeddings backend should be healthy. What's missing is an explicit 'do not call when…' or a named alternative for querying already-indexed data.

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

Deploy Server

Other Tools