Skip to main content
Glama

SourceGeek

Search jobs (filters)

employee_search_jobs
Read-only

Search live job postings by keywords with optional geo id, company ids, date-posted, job type, experience level, onsite/remote, salary and sort filters. Returns job id, title, url, company, location, posted date; pages of 25 via start.

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": {
      "keywords": "<keywords>"
    },
    "name": "employee_search_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
limitNoMaximum items to return (1-100, default 10). Results beyond the provider's page are not fetched.
startNoOffset in steps of 25 (0, 25, 50 … max 975).
salaryNoMinimum yearly salary bucket.
jobTypeNo
keywordsYesJob title or keywords, e.g. 'senior data engineer'.
titleIdsNoTitle ids (only if known).
companyIdsNoNumeric company ids.
datePostedNo
locationIdNoGeo id.
functionIdsNoJob-function ids (only if known).
industryIdsNoIndustry ids (only if known).
onsiteRemoteNo
experienceLevelNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: it names the returned fields and states the paging model ("pages of 25 via start"). However, it leaves a real behavioral tension unexplained — the schema's limit defaults to 10 and allows up to 100 while results are only fetched from the provider's 25-item page, so an agent cannot tell how limit and start interact or whether limit>25 is wasteful.

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?

Two dense sentences, front-loaded with the primary action and keyword requirement, then return values and pagination. It is efficient overall, though the filter enumeration partially duplicates the schema and crowds out the higher-value limit/start interaction details.

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 14 parameters, no output schema, and a read-only open-world search, the description does the essential job: it declares required keywords, summarizes the filter surface, lists return fields, and gives the paging token semantics. The remaining gap is arbitrating default limit vs. the 25-per-page provider paging, which materially affects how an agent should page.

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 coverage is 64%, so the schema itself carries most parameter meaning, and the description mostly echoes filter names already present in the schema (geo id, company ids, date-posted, job type, experience level, onsite/remote, salary, sort). It adds a small amount: it frames these as optional and confirms "pages of 25 via start," reinforcing the start parameter's granularity. It says nothing new about keyword syntax, id formats (e.g., numeric company ids), or id-discovery paths for the several "only if known" id filters.

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?

States a specific verb and resource: "Search live job postings by keywords" plus the filter axes available. The scope is clear, but nothing distinguishes it from siblings such as employee_search_jobs_v2, fast_search_jobs, or precision_search_jobs, which an agent would need in order to choose correctly.

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 agent can infer this is the filtered, paginated job search tool from the enumeration of filters. There is no statement of when to prefer it over the v2/fast/precision variants, nor any precondition or exclusion (for example, that geo/company ids must be resolved first via employee_search_locations or employee_search_companies).

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