Skip to main content
Glama
Sign In

GWIX

by ai.gwix
OverviewDiscussionsAdmin

Explain pay figures and what drives them

explain_pay_figures
Read-onlyIdempotent

For questions about why a pay figure is what it is: why advertised pay differs from official pay, why it moved, why a range is wide, or whether a figure seems right. Not for getting the figures in the first place: use salary_and_hiring_report. GWIX's own analyst: answers a question with a full, sourced report that combines every relevant GWIX source (job ads, advertised pay, hiring) with official statistics (BLS, Census, ONS and other agencies), with percentiles, trends, comparisons, chart data, what it means, and a citation for every figure. Free Ask GWIX answers are used first; the result shows any credits used.

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": {
      "question": "<question>"
    },
    "name": "explain_pay_figures"
  }
}

Input Schema

NameRequiredDescriptionDefault
placeNoWith occupation_code: the city with state (Houston, TX), metro or state in the question.
countryNoWith occupation_code and no place: ISO-2 country (US, GB).
questionYesThe user's question in their words, with any place, role, company, industry or period they gave.
occupation_codeNoWhen the question names a job: its SOC 2018 code, as soc_2018:29-1141 (registered nurses). Lets the GWIX panel show a quick summary while the report is written.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real context beyond that: the report synthesizes job ads, advertised pay, hiring data plus BLS/Census/ONS statistics, includes per-figure citations, and discloses the billing model (free Ask GWIX answers consumed first, credits shown). It stops short of stating latency or that report generation is asynchronous, which is only hinted at in the occupation_code parameter.

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 correctly: the use case and the exclusion come first, then the payload description. The sourcing sentence is long and enumerative ('percentiles, trends, comparisons, chart data, what it means...'), but each clause does convey what the caller receives.

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?

There is no output schema, so the description carries the return-value burden — and it does, spelling out the sourced report, its components, and per-figure citations. Combined with full schema coverage and annotations, an agent has everything needed to call this correctly.

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 all four parameters (question, place, country, occupation_code) are already documented with their conditional usage in the schema itself. The description adds no parameter-level guidance at all, 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 (explain) and resource (pay figures) plus the exact question classes it handles: advertised vs official pay divergence, movement, wide ranges, plausibility checks. That framing separates it cleanly from the report-generating siblings without requiring schema inspection.

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?

Explicitly names the exclusion ('Not for getting the figures in the first place') and routes to the correct alternative, salary_and_hiring_report. Combined with the positive 'for questions about why...' clause, an agent has both sides of the selection rule.

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

All GWIX toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources