Skip to main content
Glama

Benchmark a role's salary

getSalaryBenchmark
Read-onlyIdempotent

What a role should pay, from comparable open roles on Clera with a posted salary. Triggers: "what should we pay for this role", "is our range competitive", "salary benchmark for a senior ML engineer in NYC".

Pass roleId for one of the company's roles, or jobDescription for a role not on Clera yet.

  • source "comparables": lead with stats (p25 / median / p75 of the comparables' base salary midpoints, sampleSize). Every figure here is base salary: OTE and variable pay are not included, so say "base" when comparing it to a role with OTE. referencePercentile is where the role's own midpoint sits among them. scope says which comparables were used: same city and similar years of experience when at least five exist, widening to the city alone and then to every role in its region. region is "us" (US roles in USD) or "europe" (roles located in Europe, EUR, GBP and CHF salaries converted to USD); name the region when you quote the numbers.

  • source "market": US roles only, fewer than five comparables. stats come from live US job postings for the title's role cluster (externalMarket, which also splits them by years of experience); say they are market-wide, not Clera roles.

  • source "estimate": neither has enough data, or a role outside the US and Europe. Lead with estimate.marketSalary, a range from current web data, and say it is an estimate.

  • source "none": not enough data; say so plainly. talentSupply gives how many candidates Clera has in that role and the median salary they expect. comparables lists up to 20 anonymised roles with stage, size, equity, years of experience and location; never present them as named companies. Amounts are USD per year.

Clera privately records this tool's inputs and results for usage tracking and support.

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": "getSalaryBenchmark"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgIdNoOrganization to act as. Only needed when you belong to more than one organization.
roleIdNoOne of the company's roles, resolved with the job tool's list command. Its own salary range gets a percentile.
jobDescriptionNoA job description or a title plus location, for a role that is not on Clera yet.

Output Schema

NameRequiredDescriptionDefault
scopeYes
statsYes
regionYes
sourceYes
estimateYes
yourRoleYes
roleNamesYes
comparablesYes
talentSupplyYes
externalMarketYes
comparableCountYes
referencePercentileYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Well beyond the readOnlyHint/openWorldHint annotations, it enumerates all four possible `source` outcomes and what each implies about data coverage (Clera comparables vs. market postings vs. web estimate vs. none). It also discloses interpretive constraints the agent would otherwise get wrong: all figures are base salary excluding OTE, amounts are USD per year, comparables are anonymised and must never be presented as named companies, and region must be stated when quoting numbers.

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 first sentence front-loads the purpose, and the four `source` bullets are tightly organized and each carry distinct operational guidance. It is long overall, and the trailing note about Clera recording inputs and results is a compliance disclosure rather than tool-use guidance, but there is little true filler.

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?

For a benchmark tool with non-obvious data-provenance behavior, the description covers input selection, per-source output shape, units/currency, anonymisation constraints, and the talentSupply side output. An output schema exists, yet the description goes further by explaining how to characterize each result to the user, which is what the calling agent actually needs.

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?

Schema coverage is already 100%, so the schema documents the parameters themselves. The description adds modest meaning on top: it frames roleId and jobDescription as mutually exclusive alternatives keyed to whether the role exists on Clera, and explains that roleId's own range receives a referencePercentile. It leaves the both-supplied or neither-supplied case unaddressed.

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?

"What a role should pay, from comparable open roles on Clera with a posted salary" names a concrete resource and the data source behind the answer, then reinforces it with three verbatim trigger phrasings. An agent can immediately tell this is a compensation-lookup tool rather than a search or question-answering tool.

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 gives a clear selection rule between the two input paths ("Pass roleId for one of the company's roles, or jobDescription for a role not on Clera yet") and lists the situations that should trigger a call. It does not name any sibling tool as an alternative or state when not to use this tool, so it stops short of full routing guidance.

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