Skip to main content
Glama
Sign In

Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72%

by io.github.Eno654
OverviewDiscussionsAdmin

oxyo_remember_belief

Idempotent

Persist a durable fact, project rule, or user preference, automatically deduplicating paraphrases and superseding contradicted older 1:1 claims while preserving 1:N additive facts. Use for standing truths; use oxyo_remember_episode for transient chronological events.

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": {
      "claim": "<claim>"
    },
    "name": "oxyo_remember_belief"
  }
}

Input Schema

NameRequiredDescriptionDefault
claimYesSingle self-contained factual statement, configuration rule, or user preference.
scopeNoProject/repo scope for conflict resolution and recall (defaults to 'global').
confidenceNoEpistemic certainty score from 0.0 (tentative) to 1.0 (verified ground truth).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / claim / description
      Added value: +"Single self-contained factual statement, configuration rule, or user preference."
    • addedInput schema / properties / confidence / description
      Added value: +"Epistemic certainty score from 0.0 (tentative) to 1.0 (verified ground truth)."
    • changedInput schema / properties / scope / description
      Previous value: -"Optional project/repo scope (default 'global')"New value: +"Project/repo scope for conflict resolution and recall (defaults to 'global')."
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds substantive behavior beyond them: paraphrases are deduplicated rather than duplicated, contradicted older claims are superseded rather than left dangling, and additive facts survive. It does not say whether superseded claims are versioned or removed, which matters for a memory-mutation tool with a revisions sibling.

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?

Two sentences with the primary purpose front-loaded and the sibling routing placed second, so an agent hits the decisive information first. The middle clause ('automatically deduplicating paraphrases and superseding contradicted older 1:1 claims while preserving 1:N additive facts') is dense but every element carries distinct behavioral weight.

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?

For a three-parameter memory-write tool with no output schema, the description covers purpose, routing, and write semantics well enough to call correctly. The remaining gap is the return value: it does not indicate whether the response reports a created id, a deduplication match, or a supersession, which would help an agent chain follow-up calls.

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 description coverage is 100%, so claim, scope, and confidence are already fully documented, including the 'global' default and the 0.0-1.0 confidence range. The description adds only indirect meaning, linking the 1:1 vs 1:N distinction to conflict resolution, without elaborating on how scope or confidence drive that behavior. Baseline 3 is appropriate.

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 (persist) and a well-defined resource class (durable fact, project rule, user preference), then adds the differentiating mechanics: paraphrase deduplication, superseding of contradicted 1:1 claims, and preservation of 1:N additive facts. An agent can distinguish this from oxyo_remember_episode 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 Guidelines5/5

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

Explicitly states the when ('standing truths') and names the alternative with the condition that selects it ('use oxyo_remember_episode for transient chronological events'). This is a clean when/when-not pair rather than an implied usage note.

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

All Oxyo (oxyo.si) — Cut Coding Agent Token & Quota Burn by up to 72% toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources