Skip to main content
Glama

ctxstore — memory that follows you across models

Move Fact

move_fact
Idempotent

Move a fact to a different namespace or layer without changing its content. Updates metadata in place — preserves fact_id, text, embedding, timestamp, and deprecation chain. Use for reclassifying facts (e.g. bootstrap-v2 refactor) without the storage bloat of store-new + soft-delete-old.

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": {
      "fact_id": "<fact_id>"
    },
    "name": "move_fact"
  }
}

Input Schema

NameRequiredDescriptionDefault
fact_idYesThe UUID of the fact to move
new_layerNoNew layer: 0=identity, 1=architecture, 2=state, 3=session. Optional.
new_namespaceNoNew namespace (e.g. 'archive', 'bootstrap-v2'). Optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Goes well beyond the annotations by enumerating exactly what is preserved: fact_id, text, embedding, timestamp, and deprecation chain — this is the key non-destructive guarantee an agent needs. Annotations already cover readOnly/destructive/idempotent, and the description reinforces them without contradiction. It does not say what happens if neither new_layer nor new_namespace is supplied, or whether an unknown namespace errors.

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?

Three tight sentences, front-loaded with the action, then the preservation guarantee, then the use case. The parenthetical '(e.g. bootstrap-v2 refactor)' is slightly internal-facing but earns its place as a concrete example.

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?

A non-destructive metadata mutation with three fully-schema-documented parameters and no output schema; the description covers the essential semantic (content preserved, IDs stable). Minor gaps: no statement about the no-op case or what the response confirms.

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 description coverage is 100%, so fact_id, new_layer and new_namespace are already fully documented including the layer enum values. The description only restates the namespace-or-layer concept at a high level and adds no extra constraints (e.g. behavior when both are omitted, namespace existence validation). 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?

Specific verb+resource ('move a fact') with scope ('to a different namespace or layer'), plus an explicit statement of what is NOT changed ('without changing its content'). It differentiates itself from the store-then-soft-delete pattern, though it does not name the actual sibling tools (store_facts/delete_fact).

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 a clear use case ('Use for reclassifying facts') and implicitly names the alternative approach it replaces ('store-new + soft-delete-old') with the rationale (avoiding storage bloat). No explicit when-not or prerequisite conditions, but the selection context is clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.