Skip to main content
Glama

Search roles with Clera

searchCleraRoles
Read-onlyIdempotent

Search the open roles at startups Clera works with. Every result is a role Clera can introduce the candidate to, so this is the first search to run whenever they want roles, a company or a stack. When nothing here fits, run searchJobs straight away and show those; don't ask first.

Keep query to keywords — a title or a stack — not a sentence; leave it empty to browse newest first. When the candidate names a company, put it in company: the search then covers that company's open roles only, and an empty result means Clera has nothing open there. arrangement is remote, hybrid or on-site and widens to compatible roles the way Clera's own job matching does: hybrid also returns remote roles, on-site also returns hybrid ones, and each row's arrangement says what the role actually is. cities are exact, as the candidate names them, and countries keep roles in those countries; minSalary keeps roles with no salary on file, so an unknown salary is a question to ask, not a miss. Ranking follows the candidate's role affinity, the roles they hold and adjacent ones, and roles they declined stay hidden (undoMatchDecision brings one back).

jobFacts filters on what each role'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, like needsVisaSponsorship for someone who needs a visa; roles that don't say stay in.

status is null until the role is one of the candidate's opportunities; otherwise it is the status listMatches shows, and introRequested true means the company already asked for them. likeMatch with the row's jobId, position and companyName tells Clera they want it, and Clera may submit them to the company when it fits. readJobListing with the row's jobId has the full description. Never show jobId.

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": "searchCleraRoles"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoKeywords: a job title, a stack or a skill. Not a sentence; a company name goes in company.
citiesNoCities as the role lists them, like Berlin or London.
cursorNoPass nextCursor from a previous call to get the next page.
companyNoA company name as the talent says it. Only that company's open roles come back.
perPageNo
jobFactsNoFilters on facts read from each posting's text.
countriesNoCountry names, like "Germany" or "United States".
minSalaryNoYearly figure in the role's own currency. Roles with no salary on file stay in.
arrangementNoWidens the way Clera's matching does: hybrid also returns remote roles, on-site also hybrid ones.
visaSponsorshipNo

Output Schema

NameRequiredDescriptionDefault
foundYes
rolesYes
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?

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavior beyond them: ranking follows role affinity, declined roles stay hidden with undoMatchDecision as the recovery path, status is null until the role is an opportunity, introRequested signals company interest, and inputs/results are privately recorded. It also discloses presentation rules ('Never show jobId') and how likeMatch may submit the candidate.

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 fallback routing, and nearly every sentence carries information an agent needs (empty-result meaning, status semantics, jobId usage). It is dense and long, mixing search guidance with downstream likeMatch/readJobListing instructions, which could be separated for scanability.

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 an output schema present, return values need no explanation, and the description covers the remaining complexity: nested jobFacts filtering philosophy, salary-unknown edge case, arrangement widening, company-scoped searches, and which sibling to call next. Nothing needed to call this correctly is missing.

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 80%, so the baseline is 3, but the description goes further by explaining interactions the schema cannot: arrangement widening behaves like Clera's own matching with each row reporting the true arrangement, minSalary keeping no-salary roles means an unknown salary is a question not a miss, and jobFacts only filters on what the text says so silent roles stay in. Some fields, like perPage and cursor, are left to the schema.

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 and resource ('Search the open roles at startups Clera works with') plus the scope constraint that every result is an introducible role. It explicitly separates itself from the sibling searchJobs by naming which one to run first and what to do when this returns nothing.

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 explicit when-to-use ('first search to run whenever they want roles, a company or a stack') and when-not ('When nothing here fits, run searchJobs straight away and show those; don't ask first'). It also specifies query vs company routing and what an empty company result means, so the agent does not have to infer.

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