GetMattered

Search Jobs

getmattered_search_jobs

Read-onlyIdempotent

Search open jobs by keywords, location, seniority, job type, salary, and remote preference; return job match IDs or URLs for applying without changing your account or spending.

Instructions

Searches every open job GetMattered can apply to, by words, place, seniority and job type, whatever the user's saved search covers. Changes nothing on the account and spends nothing. Each result has the job_match_id or job_url getmattered_apply takes.

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": "getmattered_search_jobs"
  }
}

Input Schema

Name	Required	Description
`query`	No	A job title or words from one (e.g. "Founding Engineer"). Without it, the job titles in the user's job preferences.
`location`	No	A city or country (e.g. "San Francisco", "Germany") or "Remote". Without it, the countries in the user's job preferences.
`companies`	No	Companies to keep, up to 10 names.
`job_types`	No	Job types to keep: full_time, part_time, contract, internship, freelance, temporary. A job that states no type stays in.
`salary_min`	No	Lowest yearly pay in US dollars (e.g. 120000). A job that states no pay stays in.
`remote_only`	No	If true, the list holds only remote jobs.
`experience_levels`	No	Levels to keep: intern, entry, junior, mid, senior, lead, executive. A job that states no level stays in.
`posted_within_days`	No	How many days back to search by posting date, 1 to 30.
`needs_visa_sponsorship`	No	If true, jobs that rule out visa sponsorship are left out.

Output Schema

Name	Required	Description
`jobs`	Yes	Best first, each one a job GetMattered can send now. The search saved nothing.
`outcome`	Yes	found: jobs GetMattered can send now; none_found: the search ran and found none; no_query: no job title was given or saved; no_place: the location names no country GetMattered searches, or none is saved; no_remote_country: remote jobs were asked with no country given or saved.
`nextStep`	Yes
`setupStep`	No	Present while account setup is open: the first setup step.
`searchedTitles`	Yes	The job titles the search read.
`searchedCountries`	Yes	The countries the search read, as ISO codes.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.18.0Nov 13, 2026
Removedv1.10.2Oct 25, 2026
Addedv1.9.1Oct 25, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior, and the description reinforces that while adding one genuinely new fact: the call "spends nothing," which speaks to credit or quota cost that no annotation expresses. It also discloses what the result payload contains (job_match_id or job_url) so the agent knows what it can chain into apply. Gaps remain around result volume, pagination, and ordering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with purpose and scope, followed by safety/cost and then the result handoff. No filler or repetition; every clause carries information an agent can act on.

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 nine optional parameters, full schema coverage, an output schema, and complete annotations, the description supplies what the structured fields cannot: purpose, scope relative to saved searches, cost, and the downstream apply handoff. It falls short of 5 only because nothing is said about result count, ranking, or how to broaden a search that returns nothing.

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 description coverage is 100%, so every one of the nine parameters is already documented with defaults, enums, and bounds in the structured schema. The description only paraphrases the filter dimensions and adds nothing about syntax, precedence, or how filters combine, so the baseline of 3 applies.

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?

The description gives a specific verb and resource ("Searches every open job GetMattered can apply to") plus the filter axes (words, place, seniority, job type) and a scope qualifier ("whatever the user's saved search covers"). It is clear what the tool does, but it never explicitly contrasts itself with the closest sibling, getmattered_get_matches, so an agent must still infer the boundary between searching and viewing matches.

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 implied through the workflow handoff ("Each result has the job_match_id or job_url getmattered_apply takes"), which suggests search-then-apply. There is no explicit when-to-use statement, no exclusion of alternatives such as the saved-search or match-listing tools, and no stated prerequisites about the user's preferences.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server