Skip to main content
Glama

ctxstore — memory that follows you across models

Store Facts (batch)

store_facts

Store up to 50 facts in one call — the same fields as store_fact per item. Made for carrying memory over: when you already remember things about the person from your own platform memory (ChatGPT memory, Claude memory, Gemini saved info), write them here one fact per item, in their words, with the date learned when known, so the memory follows them to every other tool. Each item is stored independently; the reply lists what landed and what did not.

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": {
      "facts": "<facts>"
    },
    "name": "store_facts"
  }
}

Input Schema

NameRequiredDescriptionDefault
factsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / facts / items / properties / import
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / facts / items / properties / observed_at
      Added value: +{
      +  "type": "string"
      +}
  2. Changed3 schema fields changed
    • addedInput schema / properties / facts / items / properties / layer / maximum
      Added value: +3
    • addedInput schema / properties / facts / items / properties / layer / minimum
      Added value: +0
    • changedInput schema / properties / facts / items / properties / layer / type
      Previous value: -[
      -  "integer",
      -  "string"
      -]New value: +"integer"
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false; the description adds the important non-obvious behavior that each item is written independently and the reply reports per-item success and failure, which is exactly what an agent needs for partial-failure handling. It stops short of saying what happens on duplicates or re-runs, which matters for a tool explicitly marked non-idempotent.

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 operational constraint (50-item cap) and the field-shape reference, then the rationale, then failure semantics. The parenthetical list of platform memories is slightly padded but usefully concrete; no sentence is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no output schema and zero documented sub-fields, the description covers purpose, trigger, and partial-failure reporting, but leaves the item schema largely unexplained and says nothing about ordering, dedup, or permission/account prerequisites. Adequate to start the call, not enough to call it correctly on the first try.

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

Parameters2/5

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

Schema description coverage is 0% across an eight-field nested item (key, category enum, layer, namespace, import, observed_at, is_permanent), and the description compensates only partially: it says 'in their words' (text) and 'with the date learned when known' (observed_at) and defers the rest to store_fact's schema. Nothing explains category/layer/namespace semantics or what is_permanent versus observed_at means, so an agent must go read another tool to fill the batch correctly.

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 resource plus a hard scope ('Store up to 50 facts in one call') and explicitly links the item shape to the sibling single-fact tool ('the same fields as store_fact per item'). An agent can distinguish this batch write from store_fact without opening either schema.

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 triggering situation: when facts are already known from a platform's own memory (ChatGPT/Claude/Gemini) and should be carried over, one fact per item. It does not state the inverse case (a single new fact should go to store_fact) or when batching is inappropriate, so the routing is implied rather than spelled out.

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.