Skip to main content
Glama

Prashna accuracy against a shuffled-time control

get_prashna_calibration
Read-onlyIdempotent

Read-only. For resolved Prashna questions (outcome recorded as confirmed, partly-confirmed or not-confirmed), reports per question area how often the real-time Yes/No verdict matched what happened, beside the same question recast at random times within 30 days of asking. Returns n, hit rate, control hit rate, their difference and an insufficient-data flag under 20 scored cases. Aggregates only: no question text or tokens.

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_prashna_calibration"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost recent resolved questions to include
categoryNoLimit to one question area, e.g. career
controlSamplesNoRandom recastings per question for the control. Each is a full chart calculation, so at most 120 are run per call, newest questions first; the rest still count toward the hit rate (see controlledN).

Output Schema

NameRequiredDescriptionDefault
schemaVersionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent and closed-world behavior, and the description stays consistent with them. It adds genuinely useful context beyond the annotations: aggregates only with no question text or tokens, an insufficient-data flag under 20 scored cases, and the 30-day recast window.

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?

Front-loaded with 'Read-only' followed immediately by the core purpose, and each subsequent sentence adds distinct information (returned metrics, sample size rule, privacy constraint). Sentences are dense and long, but nothing is redundant.

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?

With an output schema present and full parameter coverage, the description need only frame intent, which it does, plus disclosure of aggregation and the minimum-data threshold. It stops short of noting behavior when no resolved questions exist or how it relates to sibling validation tools, which is a minor remaining gap for a three-parameter analytical tool.

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 coverage is 100%, so limit, category and controlSamples are already documented, including the per-call calculation cap. The description adds only the 30-day recast window and the 20-case threshold, both of which sit at the result level rather than clarifying parameter meaning, so the baseline 3 applies.

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 and resource: reports per question area how often real-time Prashna verdicts matched recorded outcomes, alongside a shuffled-time control. It also names the scope (resolved questions only) and the metric set, so an agent can separate it from calculate_prashna and record_prashna_outcome without opening a schema.

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?

It clearly gates usage on outcomes already being recorded as confirmed, partly-confirmed or not-confirmed, which implies the record_prashna_outcome prerequisite. It does not explicitly name an alternative tool or state when not to call it, so guidance is clear but not fully routable.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources