Skip to main content
Glama
Sign In
BetterDB-inc

BetterDB MCP

by BetterDB-inc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

cache_propose_threshold_adjust

Propose a semantic-cache similarity-threshold change for human review, creating a pending approval instead of applying it immediately.

Instructions

Propose a semantic-cache similarity-threshold change for review. Creates a pending proposal that requires human approval before any change is applied. Reasoning must be at least 20 characters.

Input Schema

NameRequiredDescriptionDefault
categoryNoOptional per-category override; null/undefined = global threshold
reasoningYesWhy the change is being proposed (≥20 chars)
cache_nameYesName of the semantic cache (e.g. 'betterdb_scache_prod')
instanceIdNoConnection ID; defaults to the active instance
new_thresholdYesProposed cosine-distance threshold, 0–2

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.52.0
    • removedInput schema / properties / category / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedInput schema / properties / category / type
      Added value: +[
+  "string",
+  "null"
+]
  2. Addedv0.20.2
  3. Removedv0.20.1
  4. Addedv0.17.1

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does the most important thing: it states no change is applied until a human approves, which is exactly the mutation-risk fact an agent needs. It omits permissions requirements, what the call returns (a proposal ID?), and whether a new proposal supersedes an existing pending one.

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?

Three short sentences, the action and resource first, then the safety consequence, then the constraint. Nothing is padded and nothing is buried.

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?

For a 5-parameter mutation tool with no annotations and no output schema, the description covers the approval model but leaves the return contract unstated. An agent does not learn whether it gets back a proposal ID or how to follow up with cache_get_proposal or cache_list_pending_proposals.

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 cache_name, new_threshold, category, instanceId and reasoning are all documented in structured form; that sets the baseline at 3. The only parameter detail the description repeats, the 20-character reasoning minimum, is already enforced by minLength in the schema, so it adds no new meaning.

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?

A concrete verb plus a precisely named resource: 'Propose a semantic-cache similarity-threshold change.' The phrase 'similarity-threshold' naturally separates it from the sibling proposal tools cache_propose_tool_ttl_adjust and cache_propose_invalidate, though no sibling is named explicitly.

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 second sentence implies the workflow (a pending proposal goes to human approval), which tells the agent this is the non-destructive path. But it never says when to choose this over cache_threshold_recommendation, nor that a rejection path or resubmission exists.

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