hipocampo

decay_hipocampo

Apply temporal decay to old graph links and episodic memories, archiving outdated data and removing weak links. Use dry run to preview changes before execution.

Instructions

Aplica decaimiento temporal a enlaces del grafo Y memorias antiguas.

ENLACES: peso exponencial, half-life 90 días. Elimina enlaces < 0.01. MEMORIAS: archiva episodica sin acceso ni protección a memoria_historica.

Protecciones (nunca se archivan):

nivel = automatica o semantica
metadatos.critico = true
con enlaces entrantes en memory_links

Args: dry_run: True (default) = solo lectura. False = ejecuta cambios. min_age_days: Edad mínima en días para considerar memoria candidata.

Returns: Reporte del decaimiento aplicado.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`dry_run`	No
`min_age_days`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv6.0.0Sep 8, 2026

addedInput schema / properties / min_age_days

Added value: +{
+  "default": 30,
+  "title": "Min Age Days",
+  "type": "integer"
+}

Addedv4.3.0Aug 2, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and largely succeeds: it discloses destructive effects (eliminating links < 0.01, archiving memories), a safety default (dry_run true means read-only), and explicit protected categories. It slightly underplays permanence/reversibility implications and does not explain what 'archives' means operationally, so it is not a 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?

The description is well organized into a one-line summary followed by compact sections for links, memories, protections, args, and returns. Front-loaded with purpose and zero filler, every sentence carries operational information.

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

Completeness5/5

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

For a two-parameter, no-annotation tool with an output schema, the description is complete: it covers target scope, thresholds, exclusions/protections, dry-run safety, and return value at a high level. The output schema removes the need to detail the report shape.

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 description coverage is 0%, so the description must compensate for the two parameters. It does: dry_run is explained as read-only vs. executing changes, and min_age_days is defined as the minimum age in days for a memory candidate. Minor gaps remain (whether min_age_days applies to links as well, inclusivity of the boundary), so not a 5.

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?

The description states a specific action ('Aplica decaimiento temporal') on a concrete resource set (graph links and old memories), and details exact behavior for each (exponential weight decay, half-life, eliminating links < 0.01, archiving episodic memories). This is clearly differentiated from sibling operations like delete_hipocampo, consolidate_hipocampo, or hipocampo_maintenance.

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 intended context is implied: use decay_hipocampo to age out old graph links and archive eligible memories. However, it does not explicitly state when to prefer it over sibling tools such as hipocampo_maintenance, consolidate_hipocampo, compress_hipocampo, or delete_hipocampo, nor does it give any when-not-to-use conditions beyond the listed protections.

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