Skip to main content
Glama

Search the job board

searchJobs
Read-onlyIdempotent

Search the wider job market, after searchCleraRoles. When searchCleraRoles finds nothing that fits, run this straight away and show the results; don't ask first. applyToJob applies to any of these for the candidate, so never send them off to the employer's site.

Keep query to keywords — a title, a stack, a company — not a sentence. Filters are exact values: arrangement is remote, hybrid or on-site; experienceLevel is 0-2, 2-5, 5-10 or 10+; employmentTypes are FULL_TIME, PART_TIME, CONTRACTOR, TEMPORARY or INTERN.

jobFacts filters on what each posting's text says: visa sponsorship, OPT/CPT, TN, citizenship or clearance, years required, languages, relocation, travel, on-call, people management, AI product, commission-only pay. Set the ones that follow from what the candidate told you (needsVisaSponsorship for someone who needs a visa, spokenLanguages from their languages); postings that don't say stay in. For a candidate who needs a visa use jobFacts.needsVisaSponsorship, not visaSponsorship: visaSponsorship keeps only the few listings flagged as sponsoring.

Salary is missing on most listings. minSalary keeps those unknown-salary roles in by default; pass excludeUnknownSalary to drop them, and expect a much smaller result set.

Listings the candidate passed on with passJob are left out. Use readJobListing for the full description of one result, saveJob to bookmark one, passJob to hide one, and applyToJob when they want to apply.

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": "searchJobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
queryNoKeywords: a job title, a stack, a company name. Not a sentence.
cursorNoPass nextCursor from a previous call to get the next page.
perPageNo
jobFactsNoFilters on facts read from each posting's text.
locationNoCities as the listing writes them, e.g. Berlin, London.
countriesNoCountries as the listing writes them.
minSalaryNoAnnual figure in the listing's own currency.
arrangementNo
employmentTypesNo
experienceLevelNo
visaSponsorshipNo
postedWithinDaysNo
excludeUnknownSalaryNoDrop listings with no salary on file. Most listings have none, so this cuts results hard.

Output Schema

NameRequiredDescriptionDefault
jobsYes
foundYes
hasMoreYes
nextCursorYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses non-obvious behavior: roles the candidate passed on are silently excluded, unknown-salary postings are retained by default and excludeUnknownSalary cuts results hard, and inputs/results are logged for tracking and support. That is real operational context an agent could not infer.

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 with purpose and routing, then parameters, then related tools, then a disclosure note. It earns most of its length, but restating enum values (remote/hybrid/on-site, FULL_TIME etc.) duplicates the schema and adds bulk.

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?

With 14 parameters, a nested jobFacts object and an output schema, this is a complex tool, and the description covers trigger conditions, the ambiguous filters, default-inclusion semantics, result exclusions and follow-up workflow. Pagination and sorting are covered by the schema and output schema respectively.

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 only 50%, and the description compensates for the highest-risk gap by contrasting jobFacts.needsVisaSponsorship (keeps silent postings) with top-level visaSponsorship (keeps only flagged sponsors) — a distinction invisible from the schema. It also explains that jobFacts filters on posting text and that unstated facts keep the role in, though it leaves sort, cursor, perPage, location, countries and postedWithinDays 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?

"Search the wider job market" names a specific verb and a distinct corpus, and immediately anchors it against searchCleraRoles (the narrower, Clera-internal role search). An agent can tell the two apart 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?

Explicit trigger conditions are given: run this only after searchCleraRoles finds nothing, and run it straight away without asking the candidate. It also routes follow-up actions precisely (applyToJob here rather than the employer site, readJobListing, saveJob, passJob).

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