Skip to main content
Glama

remember

Stores facts or episodes in temporal memory and flags similar current facts that may become outdated so you can link replacements and keep knowledge current.

Instructions

Guarda una memoria.

    Si es un fact, devuelve posibles reemplazos: hechos vigentes parecidos que lo nuevo
    podría dejar obsoletos. Si alguno lo está, enlázalo con supersede(old_id, new_id).
    

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": {
      "content": "<content>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNofact: verdad que puede cambiar. episode: algo que ya pasó.fact
tagsNoEtiquetas opcionales para filtrar después.
contentYesLo que hay que recordar, como una frase autocontenida.
confidenceNoSeguridad sobre lo que se guarda.
valid_fromNoDesde cuándo es verdad, en ISO 8601. Por defecto, ahora.

Output Schema

NameRequiredDescriptionDefault
memoryYes
warningsNo
next_stepNo
possible_supersedesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare it is a non-destructive write with no open-world access; the description adds the non-obvious behavior that a fact save returns candidate supersedes that the new memory may obsolete. That is real context beyond the annotations, though it does not mention deduplication, overwrite behavior, or error conditions.

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 short sentences, front-loaded with the core action and then the conditional follow-up. No filler, though the indented multi-line layout is slightly awkward and the supersede instruction could be condensed.

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?

With an output schema and full annotation coverage present, the description only needs to carry the workflow logic, which it does for the fact path. It leaves minor gaps around episode handling and idempotency, but an agent can call this correctly from what is provided.

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 earns a bump by tying the kind parameter to concrete behavioral consequences: fact triggers replacement suggestions, while episode is treated as a past event. This helps the agent choose the enum value in a way the schema blurb alone does not.

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 ("Guarda una memoria") and immediately differentiates the two behaviors: a fact returns candidate replacements while the implication is that an episode does not. It also names the related sibling supersede(old_id, new_id), though it does not distinguish itself from recall, forget, or list_memories.

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?

The description gives clear conditional guidance for the follow-up step ("Si alguno lo está, enlázalo con supersede(old_id, new_id)"), which is genuinely actionable. It does not say when to call remember versus forget or recall, nor whether to prefer fact or episode in ambiguous cases beyond the schema's own enum descriptions.

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