Skip to main content
Glama

Get calibration history

get_calibration_history
Read-onlyIdempotent

Retrieve read-only JSON calibration history rows from the sidecar metrics database, optionally filtered by model and limited in count, to review past calibration results.

Instructions

Read calibration scores from the sidecar metrics database under ~/.msty-admin. Use run_calibration_test to add rows. Read-only. Returns JSON history rows.

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_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum rows. Integer from 1 to 500. Default 50.
model_idNoOptional model id to filter. Omit for all models.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv6.2.1
    • addedInput schema / properties / limit / description
      Added value: +"Maximum rows. Integer from 1 to 500. Default 50."
    • addedInput schema / properties / model_id / description
      Added value: +"Optional model id to filter. Omit for all models."
  2. First observedv5.0.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so 'Read-only' is largely redundant. The description does add useful context beyond annotations: the storage location (~/.msty-admin) and the JSON row return shape. That is modest incremental value, consistent with a 3 against a lower bar.

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?

Four short sentences, front-loaded with purpose and storage location, followed by the write alternative and return shape. Slight waste in 'Read-only', which duplicates the readOnlyHint annotation, but otherwise tight.

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?

An output schema exists so return values need no further explanation, and the parameter schema is fully documented. The description covers purpose, storage, and the write counterpart, leaving little an agent would need missing before calling it.

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%, with limit bounds (1-500, default 50) and model_id filtering fully documented in the schema. The description adds no parameter meaning beyond that, so the baseline 3 applies.

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 verb+resource ('Read calibration scores') and locates the source ('sidecar metrics database under ~/.msty-admin'), so the agent knows exactly what is being fetched. It does not differentiate itself from similar read siblings such as bloom_get_history or get_model_performance_metrics, which keeps it from a 5.

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

Usage Guidelines4/5

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

Explicitly routes writes to run_calibration_test ('Use run_calibration_test to add rows'), giving a clear read/write split. It offers no guidance on when to prefer this over other history-reading siblings, so it stops short of full when/when-not coverage.

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