Skip to main content
Glama

supersede

Marks a stored fact as no longer true and links it to its replacement, keeping the old version in history while returning only current truth by default.

Instructions

Marca que un hecho dejó de ser verdad y lo enlaza con su versión nueva.

    El anterior se conserva en el historial, pero ya no se devuelve por defecto. Indica
    new_id o new_content, no ambos. Si el hecho ya había sido reemplazado, el error indica
    la versión vigente (current_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": {
      "old_id": "<old_id>"
    },
    "name": "supersede"
  }
}

Input Schema

NameRequiredDescriptionDefault
new_idNoId de la versión nueva, si ya la guardaste con remember.
old_idYesId del hecho que dejó de ser verdad.
reasonNoPor qué cambió (opcional).
valid_fromNoSolo con new_content: desde cuándo es verdad lo nuevo.
new_contentNoTexto de la versión nueva, si todavía no la guardaste.

Output Schema

NameRequiredDescriptionDefault
newYes
oldYes
warningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare a non-read-only, non-destructive, closed-world mutation. The description adds real value beyond that: the old version is retained in history but excluded from default results, and the already-superseded case surfaces current_id. It still says nothing about return payload, idempotency, or whether the operation can be undone.

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 core action in the first sentence, followed by retention behavior, the parameter constraint, and the error path. Dense and purposeful, with only minor line-break artifacts and no filler.

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?

An output schema exists, so return values need not be described, and the description covers the mutation's side effects, the mutual-exclusion rule, and the already-replaced error case. What remains missing is how this differs from a forgetting/deletion tool, which matters for an agent choosing among the memory siblings.

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 adds a genuine constraint the schema cannot express: new_id and new_content are mutually exclusive alternatives. The rest (what old_id and reason mean, valid_from only with new_content) is left to the schema.

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 action on a specific resource: marks a fact as no longer true and links it to its new version, plus what happens to the old record. It implicitly contrasts with a delete-style tool by noting the previous version stays in history, but it never names a sibling, so routing is inferential rather than explicit.

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 concrete conditional guidance: supply new_id or new_content but not both, and if the fact was already replaced the error reports the current_id, which tells the agent how to recover. It stops short of stating when to use this instead of forget or remember.

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