Skip to main content
Glama
Sign In
llmledger

llmledger

by pouriaetab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Forecast Job

forecast_job
Read-onlyIdempotent

Estimate a whole job's time, cost, accuracy, price-change risk, and break-even from a promptfoo sample when total test count is known.

Instructions

Estimate a whole job's time, cost and accuracy from a promptfoo run of a sample of it: for each model in the sample, the time as a usual time and a slow day, the cost at its cheapest listing next to the listing the sample used, the 90-day chance of a price change, how often it was right (95% range) and the break-even against the pick. Use when a promptfoo results file of a sample exists and the whole job's size is known. Not for a job with no sample (estimate_cost for money, estimate_time for time).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "promptfoo_results": "<promptfoo_results>",
      "items": "<items>"
    },
    "name": "forecast_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
wayNoHow the models are called (default: read from each provider)
itemsYesHow many tests the whole job has
thinkingNoThinking turned on
concurrencyNoCalls running at once in the whole job (default: as the sample ran)
promptfoo_resultsYesPath of a promptfoo results file from a sample of the job (promptfoo eval --filter-sample 20 -o sample.json)
wrong_answer_costNoDollars a wrong answer costs you to catch and fix; the pick then counts it

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.7

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered. The description adds genuine estimation semantics beyond that (that cost is reported at the cheapest listing next to the listing the sample used, that accuracy carries a 95% range, that break-even is computed against the pick), which tells the agent how to interpret the numbers. It stops short of stating assumptions or limits on the extrapolation, so not a 5.

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 lead clause front-loads the action and resource, and the trailing sentences carry routing information rather than filler. It is dense and slightly run-on in the output enumeration, but nearly every clause earns its place by naming a distinct reported metric.

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

Completeness5/5

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

An output schema already defines return values, annotations cover the safety profile, and schema coverage is 100%, so the description only needs to convey purpose, preconditions and sibling routing — all of which it does. Nothing an agent needs to select or invoke this tool correctly is missing.

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 every parameter (way, thinking, concurrency, wrong_answer_cost, items, promptfoo_results) is already documented in the schema, setting the baseline at 3. The description references the sample and the whole job's size but adds no format or defaulting nuance beyond the schema text.

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 names a specific verb (estimate) and resource (a whole job's time, cost and accuracy) and enumerates exactly which outputs are produced: usual/slow-day time, cheapest-vs-used listing cost, 90-day price-change chance, accuracy range and break-even. It also distinguishes itself from the similar-sounding siblings by requiring a promptfoo sample, so an agent can separate it from estimate_cost/estimate_time 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 Guidelines5/5

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

Explicit precondition: 'Use when a promptfoo results file of a sample exists and the whole job's size is known.' Explicit exclusion plus named alternatives: 'Not for a job with no sample (estimate_cost for money, estimate_time for time).' Both the when and the when-not, with the correct fallback tools, are stated outright.

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