Skip to main content
Glama

Firecrawl by Nova (CIVAI)

jobs_search

Find job postings and check whether a posting is still open. Use it to: find jobs by role and place (query, with location, remote or posted_within_days); read one posting by url and tell whether it is still open; check up to 10 posting urls in one call; list a company's open roles from its own job board (company, a name or domain; add query for one role there); and see who is hiring for a role (query with group_by "employer"). Every row has the same normalized fields: title, company, location, remote, posted_at as the board states it, url, source, a status, and checked_at, the time Firecrawl read it. status is open when the posting was read from the employer's board or live posting page in this call, and unverified when it comes from a job site and was not confirmed on the employer's board. A posting checked by url can also be closed, not_found or error. A single url returns the full description; list rows carry it with include_description. A company search names the boards it read and what each covers; when no board is found, rows come from job sites and notes says so. boards_only searches employers' own boards only. Each provider read is charged its listed price; max_credits caps the call. Example: {"query":"data engineer","location":"Berlin","posted_within_days":14}.

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": {
      "objective": "<objective>"
    },
    "name": "jobs_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoOne posting URL to read in full and check: whether it is still open, with its description.
urlsNoUp to 10 posting URLs to check in one call; each comes back with its status.
limitNoRows wanted from a search by query or company, 1 to 100, default 10. Leave it out with url or urls.
queryNoJob title or keywords, e.g. "data engineer". With company, the role to look for there.
cursorNonext_cursor from an earlier call with the same input, for more rows.
remoteNotrue returns remote roles only.
companyNoCompany name or domain, e.g. "example.com". Lists that company's open roles from its own job board.
group_byNo"employer" groups the postings found by employer, to see who is hiring for a role.
locationNoCity, region or country, e.g. "Berlin" or "Canada".
providerNoAsk only this provider, e.g. "indeed". Leave it out to let Firecrawl choose.
objectiveYesThe user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words.
boards_onlyNotrue searches employers' own job boards only; every row is confirmed open on its board.
max_creditsNoMost credits the call may spend. Set it only to a budget the user gave; left out, it is 200. A provider that could pass it is not started.
posted_within_daysNoOnly postings the board dates within this many days, 1 to 365.
include_descriptionNotrue adds the description to each list row. A single url always returns it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / objective / description
      Previous value: -"The user's underlying goal for this call, in one sentence: what they are ultimately trying to accomplish, not a restatement of the URL or query. Reuse it across related calls. Avoid sensitive information."New value: +"The user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words."
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full disclosure burden and does so unusually well: it defines the status vocabulary (open, unverified, closed, not_found, error) and what each means about provenance, explains that each provider read is charged its listed price, that max_credits caps the call and defaults to 200, and that a provider which could exceed the budget is not started. It also discloses failure behavior ("when no board is found, rows come from job sites and notes says so") and that a company search names the boards it read and their coverage.

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?

It is front-loaded with purpose and modes, then normalizes into return fields, status semantics, and cost behavior, closing with a concrete example call. At roughly 230 words it is on the long side for a description, but nearly every sentence introduces a distinct fact (provenance, status values, billing, board fallback) rather than restating the name. Slight density cost keeps it from a 5.

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?

For a 15-parameter, multi-mode tool with no output schema, the description enumerates the return row fields (title, company, location, remote, posted_at, url, source, status, checked_at) and explains the status column, which compensates for the missing output schema. Pagination is only implied via the schema's cursor field, and nothing is said about response shape when a batch url check partially fails, leaving a small gap for a tool this complex.

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 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema states only per-field: url and urls are mutually exclusive with limit ("Leave it out with url or urls"), query doubles as a role filter when company is set, boards_only changes row certainty, and include_description is unnecessary with a single url. Those interaction rules are genuine added meaning. It does not, however, explain cursor/pagination or provider naming beyond what the schema already says.

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?

Opens with a specific verb-and-resource pair ("Find job postings and check whether a posting is still open") and then enumerates the five distinct modes (query search, single url read, batch url check, company board, employer grouping). An agent can tell exactly what resource domain this covers and which mode matches its intent without opening the schema.

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?

Mode routing is explicit: "read one posting by url", "check up to 10 posting urls in one call", "add query for one role there" when using company, and group_by "employer" "to see who is hiring for a role". It also states boards_only "searches employers' own boards only", which is a real selection criterion. What is absent is any exclusion or named alternative outside this tool (e.g. when to prefer a general web search over this), so it stops short of a 5.

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