Skip to main content
Glama
Sign In
kernl

kernl

by fastslack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kernel_facts_assert

Record a time-stamped fact about a person, thing, or user; new values end or correct old ones while preserving history so memory avoids contradictory answers.

Instructions

Record a fact about a person, thing or the user — subject, predicate, value — with when it became true. A new value for the same subject and predicate ends the old one (mode change) or replaces it as a mistake (mode correction); the history is kept, so the memory does not hold two contradicting answers. Saying the same thing again changes nothing.

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": {
      "subject": "<subject>",
      "predicate": "<predicate>",
      "object": "<object>"
    },
    "name": "kernel_facts_assert"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNochange: the world changed — the old value stays in the history, true until this one began. correction: the old value was wrong — it is replaced over the same span.change
multiNoSeveral values can be true at once (speaks, likes). Default: a new value replaces the old one.
objectYesThe value.
sourceNoWhere it came from: chat, agent, mail, user…
subjectYesWho or what the fact is about. A node reference ("Person:<contact id>", "Task:<id>") links it in the graph; "me" for the user; otherwise a plain name.
predicateYesWhat is said about it, short and reusable: "works_at", "lives_in", "prefers", "birthday".
confidenceNo
source_refNoId of the message, run or row it came from.
valid_fromNoWhen it became true (ISO date or time). Default now.
subject_nameNoReadable name of the subject, when `subject` is a reference.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does it well: it discloses that history is preserved, that two contradicting answers are never both live, that mode=change ends the old value versus mode=correction rewriting the same span, and that re-asserting an identical fact is a no-op. That idempotency and non-contradiction guarantee is exactly the kind of context annotations would otherwise supply. It does not cover failure modes, permission needs, or what the response returns, keeping it below 5.

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 tight sentences, front-loaded with the verb and the triple structure, then the conflict-resolution rule, then the idempotency guarantee. Every sentence carries distinct information and nothing is padded.

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 10-parameter temporal fact store with an output schema, the description covers the conceptual model an agent needs to pick the right mode and avoid accidental overwrites. Return values needn't be explained since an output schema exists. Minor gaps remain around confidence/source semantics and how multi-valued predicates evolve, but nothing essential to a correct call is missing.

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 90% and the schema already explains mode, multi, subject references, predicate style, and valid_from in detail. The description reiterates the mode semantics (change vs correction) rather than adding syntax or edge-case rules the schema lacks, such as how multi=true interacts with an existing single value. With the schema doing the heavy lifting, the baseline 3 applies.

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: 'Record a fact about a person, thing or the user — subject, predicate, value — with when it became true.' An agent immediately knows this is a write of a temporal triple. It doesn't name a sibling such as kernel_facts_retract or kernel_facts_query to delineate boundaries, so it stops short of a 5.

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 only implied by the description of the operation itself; there is no explicit 'use this when…' directive and no named alternative for removing or querying facts. The mode/multi explanations border on behavioral semantics rather than when-to-use guidance. An agent can infer the use case, but the definition leaves routing between siblings to inference.

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