Compass OS: Career

get pay range

get_pay_range

Read-onlyIdempotent

Summarize posted yearly pay (USD) for the roles the user is searching for, from their job scans and tracked roles: low, median and high, how many postings it's from, last week's median when it's comparable, and a few roles hiring now with their pay. Use it for salary questions about the search as a whole; one role's pay is on its posting. Read-only. With too few postings that list pay, it says so and gives Glassdoor's estimate when there is one: always call that a Glassdoor estimate with its sample size and date, never posted pay.

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_pay_range"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`text`	Yes	The answer, or what was done, in plain words for the user: the same text as content
`undo`	No	On a saved write: its undo handle, for undo within 24 hours
`widget`	No	The card the host draws with it, e.g. "pipeline"; "confirm" means a write waits for the user's Yes and nothing is saved yet

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds non-obvious behavior: the currency/period basis (yearly, USD), the conditional "last week's median when it's comparable", and the low-sample fallback that returns a Glassdoor estimate with sample size and date. The labeling obligation (never present an estimate as posted pay) is real behavioral context an agent would otherwise get wrong; the only minor gap is that it doesn't say whether results are cached or how staleness is signalled.

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-loads the purpose and scope, then the routing rule, then the fallback caveat — a sensible priority order with no filler. The final sentence is long and packs two separate ideas (the fallback trigger and the required attribution), which slightly costs readability but still earns its place.

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 exists, yet the description still orients the agent on what the summary contains, which nodes are conditional, and how to characterize an estimate. For a zero-parameter, read-only aggregate tool this covers everything needed to call and report it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters, so the baseline is 4; there is no parameter meaning for the description to add or omit. The description correctly spends its words on scope and output semantics instead of inventing inputs.

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?

Opens with a specific verb and resource ("Summarize posted yearly pay (USD) for the roles the user is searching for") and enumerates the returned statistics (low, median, high, posting count, prior-week median, sample hiring roles). It also explicitly scopes itself against the sibling case — "one role's pay is on its posting" — so an agent can separate it from get_job without opening either 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?

Gives an explicit when-to-use rule ("salary questions about the search as a whole") and an explicit alternative for the other case (a single role's pay lives on its posting). It also covers the edge-case branch: what happens when too few postings list pay.

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

All Compass OS: Career tools Inspect

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

Need Help?