Skip to main content
Glama

Search jobs by driving commute

search_jobs
Read-onlyIdempotent

Search the offpeak.fyi public job board; every result has a public job page URL (https://offpeak.fyi/jobs/) with an Apply link to the employer. Anonymous searches require filters.origin as {lat,lng}; filters.home is only a display label. Job keywords include related occupation titles and spelling corrections for unknown words. Saved filters are available with filters:read; otherwise an explicit origin is required. Overrides never save preferences. Drive times use typical weekday rush-hour traffic. Returns a stable result snapshot, one fastest site per job. Pagination accepts cursor=next_cursor and optionally limit, without filters; cursors expire after 15 minutes.

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": "search_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
cursorNoOpaque next_cursor from the previous page. Omit filters when continuing; expires after 15 minutes.
filtersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / filters / properties / origin / description
      Previous value: -"Driving start coordinates. Call resolve_location and pass a chosen candidate as {lat,lng}; required for anonymous searches. Null clears a saved origin."New value: +"Driving start coordinates. Coordinates as {lat,lng}; required for anonymous searches. Null clears a saved origin."
  2. Changed9 schema fields changed
    • changedInput schema / properties / filters / properties / function / description
      Previous value: -"Function code from get_filter_options; empty string clears."New value: +"Function code from get_filter_options, or several comma-separated to match any of them; empty string clears."
    • changedInput schema / properties / filters / properties / function / maxLength
      Previous value: -40New value: +400
    • changedInput schema / properties / filters / properties / industry / description
      Previous value: -"Industry code from get_filter_options; empty string clears."New value: +"Industry code from get_filter_options, or several comma-separated to match any of them; empty string clears."
    • changedInput schema / properties / filters / properties / industry / maxLength
      Previous value: -40New value: +400
    • changedInput schema / properties / filters / properties / level / description
      Previous value: -"Seniority inferred from title and experience; empty string clears."New value: +"Seniority inferred from title and experience: intern, entry, mid, senior, manager or director, or several comma-separated to match any of them; empty string clears."
    • removedInput schema / properties / filters / properties / level / enum
      Removed value: -[
      -  "",
      -  "intern",
      -  "entry",
      -  "mid",
      -  "senior",
      -  "manager",
      -  "director"
      -]
    • addedInput schema / properties / filters / properties / level / maxLength
      Added value: +100
    • addedInput schema / properties / filters / properties / level / pattern
      Added value: +"^((intern|entry|mid|senior|manager|director)(,(intern|entry|mid|senior|manager|director))*)?$"
    • changedInput schema / properties / filters / properties / sort / description
      Previous value: -"Shortest commute, newest first, or highest annualized pay first; default commute."New value: +"Closest (shortest commute), newest first, or highest annualized pay first; default commute."
  3. Changed1 schema field changed
    • changedInput schema / properties / filters / properties / max_minutes / description
      Previous value: -"Maximum one-way driving minutes, excluding live traffic; default 20."New value: +"Maximum one-way driving minutes; default 20."
  4. Changed14 schema fields changed
    • addedInput schema / properties / cursor / description
      Added value: +"Opaque next_cursor from the previous page. Omit filters when continuing; expires after 15 minutes."
    • removedInput schema / properties / cursor / pattern
      Removed value: -"^[a-f0-9]{64}\\.[a-f0-9]{32}$"
    • addedInput schema / properties / filters / properties / function / description
      Added value: +"Function code from get_filter_options; empty string clears."
    • addedInput schema / properties / filters / properties / home / description
      Added value: +"Display label only; never geocoded. Pass origin coordinates to search."
    • addedInput schema / properties / filters / properties / include_near_misses / description
      Added value: +"Include routed jobs up to 1.5 times max_minutes; default false."
    • addedInput schema / properties / filters / properties / include_no_pay / description
      Added value: +"Include unknown pay when min_pay is set; default true."
    • addedInput schema / properties / filters / properties / industry / description
      Added value: +"Industry code from get_filter_options; empty string clears."
    • addedInput schema / properties / filters / properties / level / description
      Added value: +"Seniority inferred from title and experience; empty string clears."
    • addedInput schema / properties / filters / properties / max_minutes / description
      Added value: +"Maximum one-way driving minutes, excluding live traffic; default 20."
    • addedInput schema / properties / filters / properties / min_pay / description
      Added value: +"Minimum annual USD pay, using posted range midpoint and 2080 hours/year; 0 clears."
    • addedInput schema / properties / filters / properties / origin / description
      Added value: +"Driving start coordinates. Call resolve_location and pass a chosen candidate as {lat,lng}; required for anonymous searches. Null clears a saved origin."
    • addedInput schema / properties / filters / properties / query / description
      Added value: +"Title/company words or related occupation titles; empty string clears."
    • addedInput schema / properties / filters / properties / saved_only / description
      Added value: +"Intersect results with account bookmarks; requires jobs:read; default false."
    • addedInput schema / properties / filters / properties / sort / description
      Added value: +"Shortest commute, newest first, or highest annualized pay first; default commute."
  5. Changed2 schema fields changed
    • addedInput schema / properties / cursor
      Added value: +{
      +  "pattern": "^[a-f0-9]{64}\\.[a-f0-9]{32}$",
      +  "type": "string"
      +}
    • removedInput schema / properties / offset
      Removed value: -{
      -  "default": 0,
      -  "maximum": 100000,
      -  "minimum": 0,
      -  "type": "integer"
      -}
  6. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds substantive behavior on top: stable snapshot with one fastest site per job, drive times based on typical weekday rush-hour traffic, cursors expiring after 15 minutes, and the fact that overrides never persist preferences. That is exactly the kind of context annotations cannot carry.

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 result semantics, then auth/pagination rules; every sentence carries information. It is dense and slightly sprawling (six clauses covering auth, keywords, returns, and pagination in one block), which keeps it just under the top mark.

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?

There is no output schema, and the description does sketch the result shape (stable snapshot, one fastest site per job, public job page URL with Apply link) plus pagination and auth prerequisites. It omits what error/failure states or empty-result behavior look like, so it is solid but not exhaustive for a search over a nested filter object.

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?

Top-level coverage is low (33%), but the description compensates on the genuinely confusing points: filters.home is a display label never geocoded, origin is required for anonymous searches, and keywords expand to related occupation titles and spelling corrections. The nested schema already documents sort/level/min_pay/etc., so the remaining gap is small.

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 the offpeak.fyi public job board') and the title narrows it to driving-commute search, which separates it from the browsing siblings like get_jobs/get_job. It never names those siblings or explains the boundary, so an agent still has to infer when to pick search_jobs over get_jobs.

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?

Gives concrete conditional guidance: anonymous searches require filters.origin, saved filters need filters:read, and pagination must omit filters and use cursor with an optional limit. It stops short of routing the agent to alternatives (get_jobs, resolve_location for coordinates, get_filter_options for codes), so usage is clear but not fully comparative.

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