Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_brain_recall

Surface everything related to a topic across tasks, notes, contacts, communications, reminders, and events in one ranked semantic recall result.

Instructions

Unified semantic recall across ALL modules — tasks, notes, contacts, communications, reminders, calendar events — in one ranked result. Use this to surface everything related to a topic regardless of which module it lives in. Ranking blends embedding similarity with a learned per-item weight that adapts to how you use results.

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": {
      "query": "<query>"
    },
    "name": "kernel_brain_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindsNoRestrict to item kinds: task, note, contact, comm, reminder, event.
limitNo
queryYesFree-text query. Searches the unified space across all modules.
hybridNoBlend dense embedding similarity with lexical overlap (rescues exact-term matches the embedding misses).
resolve_rowsNoAlso fetch the exact source row for each hit.
cosine_weightNoHybrid weight on the dense leg; lexical gets 1 − this.
min_similarityNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it discloses a genuinely non-obvious trait: results are ranked by a blend of embedding similarity and a learned per-item weight that adapts to prior usage, so ordering is personalized rather than static. It omits read-only confirmation, any scope/permission constraints, and result-count behavior, which are lower-stakes for a recall operation with an output schema.

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 sentences, zero filler: scope first, usage directive second, ranking behavior last. Every sentence adds information not present in the schema or structured fields.

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?

For a 7-parameter tool with no annotations but an output schema, the description covers what it searches, when to pick it, and how results are ordered. Remaining gaps (limit/min_similarity behavior, whether source rows are returned by default) are mostly covered by the schema defaults and output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 71%, so kinds, hybrid, and cosine_weight are already documented in the schema and the description adds no format or tuning guidance beyond restating the ranking blend. Parameters like limit, min_similarity, and resolve_rows get no treatment in the description, leaving a modest compensation gap.

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+resource ('semantic recall') and enumerates the covered modules (tasks, notes, contacts, comms, reminders, events), so the agent knows this is the cross-module search rather than a module-scoped one. The 'across ALL modules' emphasis implicitly separates it from narrower siblings, but no sibling is named, so the contrast with an ask-style tool is left to inference.

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?

'Use this to surface everything related to a topic regardless of which module it lives in' gives a clear selection rule for the cross-module case. It stops short of stating when NOT to use it (e.g. single-module or conversational lookups) and names no alternative tool.

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