Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

get_calibration_health_recommendations

Read-only

Recommends how many observations per category Kiln should require before changing your calibration, suppressing suggestions below a configurable sample threshold.

Instructions

Suggest how much evidence Kiln should want before it changes your calibration.

Needs Kiln Pro.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_calibration_health_recommendations"
  }
}

Input Schema

NameRequiredDescriptionDefault
min_samples_per_categoryNoBelow this count of observations in a category, the recommendation is suppressed. Default 5; raise it for stricter statistical confidence. Default: 5.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.5.1
    • changedInput schema / properties / min_samples_per_category / description
      Previous value: -"Default: 5."New value: +"Below this count of observations in a category, the recommendation is suppressed.  Default 5; raise it for stricter statistical confidence. Default: 5."
  2. Addedv1.5.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered by structured data. The description adds one piece of non-schema context the annotations lack: the Kiln Pro entitlement requirement. It still says nothing about what a recommendation contains or whether it is advisory-only versus tied to an actual calibration change.

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 short sentences, front-loaded purpose followed by the entitlement constraint, with no filler. It is efficient but borders on under-specified rather than over-written.

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 one-optional-parameter read-only tool with no output schema, the minimum an agent needs is present: what it advises about and the Pro requirement. However, the meaning of "health recommendations" and how the output relates to the calibration workflow is left undefined, which matters given how many calibration siblings exist.

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% for the single optional parameter (min_samples_per_category, with default and tightening guidance), so the schema carries the semantics. The description adds no further information about the threshold, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Suggest how much evidence Kiln should want before it changes your calibration" conveys the general idea (advising on sample-size/evidence thresholds) but is oblique rather than a crisp statement of what is returned. With many calibration siblings (assess_calibration_status, classify_calibration_confidence, apply_calibration_recommendations, get_calibration_freshness), the description does nothing to separate this tool from them.

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 only guidance is the eligibility gate "Needs Kiln Pro." There is no statement of when to call this versus assess_calibration_status or apply_calibration_recommendations, and no indication of prerequisites beyond the plan tier.

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