Skip to main content
Glama
Mibayy

token-savior

by Mibayy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_admin

Destructive

Run memory maintenance operations such as status checks, diagnostics, deduplication sweeps, distillation, garbage collection, consistency checks, and vector reindexing through a single dispatch.

Instructions

Single dispatch for all memory admin / maintenance ops (status, doctor, dedup_sweep, distill, roi_gc, consistency, vector_reindex, etc.).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opYesWhich memory-admin sub-operation to run.
limitNoPagination/limit (where applicable).
dry_runNoPreview-only mode for sweeps/garbage collectors.
rebuildNovector_reindex: re-embed rows that already have a vector, not just the missing ones.
project_rootNoFilter by project (where applicable).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.24.0
    • addedInput schema / properties / rebuild
      Added value: +{
+  "description": "vector_reindex: re-embed rows that already have a vector, not just the missing ones.",
+  "type": "boolean"
+}
  2. Addedv4.0.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered structurally. The description adds only that this is a multiplexed dispatch and names a few ops, without saying which ops destroy data, whether dry_run is advisable first, or what the destructive operations affect.

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?

A single front-loaded sentence with no filler, though the trailing 'etc.' is imprecise for an enum that is fully enumerable in the schema and slightly weakens the specification.

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

Completeness2/5

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

For a 21-op dispatch tool with no output schema, the description should at least group or explain the ops; instead it names a handful and defers with 'etc.'. An agent cannot determine from this text what 'distill', 'roi_gc', 'from_bash', or 'set_global' do, leaving the definition materially incomplete.

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 coverage is 100% and each parameter (op, limit, dry_run, rebuild, project_root) carries its own description, so the schema does the heavy lifting. The description enumerates only 7 of the 21 enum values and adds no semantics for what individual ops do, so it does not meaningfully exceed the baseline.

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 purpose: a single dispatch entry point for memory admin/maintenance operations, and lists representative op names (status, doctor, dedup_sweep, distill, roi_gc, consistency, vector_reindex). This distinguishes it at a high level from the memory_save/search/get/delete CRUD siblings, though it does not clarify overlap with neighbors like reindex or find_semantic_duplicates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance is given, and no alternatives are named. The agent is left to infer from 'admin / maintenance ops' that this is the maintenance entry point, but nothing states which sibling to prefer for overlapping tasks.

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