Skip to main content
Glama
Cloto-dev

CPersona

Official
by Cloto-dev
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

calibrate_threshold

Auto-calibrate the vector search threshold by sampling memory pairs and placing it above the null cosine distribution, rejecting unrelated memories without labeled data.

Instructions

Auto-calibrate the vector search threshold from the null (random-pair) cosine distribution. Samples random memory pairs and places the threshold ABOVE the null mean so unrelated pairs are rejected. method='separation' (default) learns the operating point from two populations — null pairs vs temporally-adjacent same-session positives (nearest-neighbour fallback when too few exist); method='percentile' uses a quantile of the null distribution (robust to anisotropic models such as bge-m3); method='zscore' uses mean + z*std. No labels used, purely statistical. Adapts to both embedding model and corpus characteristics.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
methodNo'separation' (default; two-population — learns the operating point from null pairs vs temporally-adjacent same-session positives, falling back to nearest-neighbour when too few exist), 'percentile', or 'zscore'
agent_idYesAgent ID whose memories to sample
z_factorNoZ-score multiplier for method='zscore' (default: 1.0, higher = stricter)
percentileNoNull-distribution quantile for method='percentile' (default: 0.95, higher = stricter)
sample_sizeNoNumber of embeddings to sample (default: 200)
session_keyNoOpaque session identity you declare: a partition hint, not authentication and not a data filter. Selects which no-persist pause applies to this call. Omit to share one bucket with every caller that omits it. Full text on recall.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changedv2.5.10
    • addedInput schema / properties / session_key
      Added value: +{
+  "default": "",
+  "description": "Opaque session identity you declare: a partition hint, not authentication and not a data filter. Selects which no-persist pause applies to this call. Omit to share one bucket with every caller that omits it. Full text on recall.",
+  "type": "string"
+}
  2. Changed1 schema field changedv2.5.4
    • addedInput schema / properties / method / enum
      Added value: +[
+  "separation",
+  "percentile",
+  "zscore"
+]
  3. Addedv2.5.2
  4. Removedv2.5.1
  5. Changed3 schema fields changedv2.4.34
    • addedInput schema / properties / method
      Added value: +{
+  "description": "'percentile' (default), 'zscore', or 'separation' (two-population, learns the operating point from null vs nearest-neighbour positives)",
+  "type": "string"
+}
    • addedInput schema / properties / percentile
      Added value: +{
+  "description": "Null-distribution quantile for method='percentile' (default: 0.95, higher = stricter)",
+  "type": "number"
+}
    • changedInput schema / properties / z_factor / description
      Previous value: -"Z-score multiplier (default: 1.0, higher = stricter)"New value: +"Z-score multiplier for method='zscore' (default: 1.0, higher = stricter)"
  6. 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 say the operation is not read-only, not idempotent, and not destructive. The description adds meaningful behavioral detail: it samples memory pairs, places the threshold above the null mean, uses no labels, and adapts to model and corpus. It stops short of explicitly stating whether the calibration result is persisted or how it affects future recalls, but the added algorithm-level transparency is strong.

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?

The description is dense but well-structured: purpose first, then method details. Every sentence adds meaningful information, though the method explanations are slightly verbose and overlap with the schema descriptions.

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

Completeness3/5

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

The description covers the algorithm and method choices well, but it does not state what the calibration changes in persisted state, whether there are prerequisites (e.g., existing memories), or what the return value is. Given the absence of an output schema and the mutating nature of the tool, these gaps leave the description slightly incomplete.

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. The description goes beyond the schema by explaining the statistical rationale for each method, including when percentile is robust (anisotropic models like bge-m3) and how separation falls back to nearest-neighbour. This helps an agent choose sensible parameter values.

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 clearly states a specific action ('Auto-calibrate') on a specific resource ('the vector search threshold'), grounded in a concrete statistical basis (the null cosine distribution). It also distinguishes the different calibration methods, making the tool's intent unambiguous.

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?

The description explains how the tool works and the method options, but it does not say when to use this tool versus alternatives like set_recall_precision or get_recall_precision. It gives no explicit usage conditions, prerequisites, or exclusion criteria.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Cloto-dev/CPersona'

If you have feedback or need assistance with the MCP directory API, please join our Discord server