SiteCheck Jobs & Property

Tech compensation for one company and job family

jobs_levels_fyi

Read-only

Tech compensation for one company and job family from Levels.fyi's public salary page (e.g. google + software-engineer): total-comp, base, stock and bonus percentiles (p10-p90) with sample size, and the average package per level (L3, L4 ...) with typical years of experience. United States figures in USD as published; reflects user-reported data. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

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": {
      "company": "<company>"
    },
    "name": "jobs_levels_fyi"
  }
}

Input Schema

Name	Required	Description	Default
`company`	Yes	Company slug as in Levels.fyi URLs, e.g. google, meta, amazon, stripe
`jobFamily`	No	Job family slug, e.g. software-engineer, product-manager, data-scientist (default software-engineer)

Output Schema

Name	Required	Description	Default
`bonus`	No
`levels`	No
`source`	No
`company`	No
`country`	No
`currency`	No
`dataDate`	No
`checkedAt`	No
`jobFamily`	No
`baseSalary`	No
`sampleSize`	No
`stockPerYear`	No
`totalCompensation`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A3.9/5.0

Behavior5/5

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

The annotations only declare readOnlyHint and openWorldHint; the description adds substantial context they do not cover. It discloses x402 pricing ($0.002 USDC per successful call on Base, Solana or Arc) with the important guarantee that failed calls are not charged, plus the data's provenance (user-reported) and geographic/currency limitation (US figures only, as published). For a paid third-party API these are the exact behaviors an agent must know before calling.

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 purpose, scope, and returned fields are front-loaded in one dense sentence, and the payment terms are separated into a second sentence where they belong. It is information-dense rather than padded, though the parenthetical field enumeration is long enough to slow scanning slightly.

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, the description need not explain return values, yet it still summarizes them usefully and adds pricing, provenance, and currency scope. The only untreated areas are data freshness/update cadence and error behavior for unsupported company or job-family slugs.

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% and both parameters already carry examples and the jobFamily default, so the baseline applies. The description's inline examples restate what the schema provides and add no new slug-format rules, normalization guidance, or behavior for unknown companies.

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?

The description names the exact resource (tech compensation for one company and job family), the source (Levels.fyi's public salary page), and the returned fields (total-comp, base, stock, bonus percentiles p10-p90, sample size, average package per level with years of experience). That is enough to distinguish it from the surrounding job-board siblings. It falls short of 5 only because it never explicitly contrasts itself with the closest sibling, jobs_payscale.

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

Usage Guidelines3/5

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

Usage is only implied: the 'e.g. google + software-engineer' input pattern tells the agent this is a lookup keyed by company plus job family. There is no explicit statement of when to prefer this over jobs_payscale or a job-board sibling, and no exclusions. Adequate for a simple two-parameter lookup, but the routing decision is left to inference.

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

All SiteCheck Jobs & Property 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?