Skip to main content
Glama

Resume Booster Job Board

Search jobs (research shape)

search
Read-onlyIdempotent

An ALIAS of search_jobs in the fixed shape ChatGPT's deep-research and company-knowledge connectors call: one query string in, {results:[{id,title,url}]} out. Every result's id is the job id fetch and every other tool take; title adds employer, place and the employer's posting date; url opens the posting on resumebooster.work in a browser. Same board, same ranking and the same 10-row page as a keyless search_jobs; the disclosures ride beside the results. Any other client should call search_jobs, which takes every filter.

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": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesFree text — title, skills, a place, exclusions with a leading minus.

Output Schema

NameRequiredDescriptionDefault
noteNo
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed18 schema fields changed
    • removedOutput schema / additionalProperties
      Removed value: -true
    • removedOutput schema / properties / agenciesExcluded
      Removed value: -{
      -  "description": "Row-selecting: disclosed agency inventory is hidden from this page.",
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / countUnavailable
      Removed value: -{
      -  "description": "The board could not count this query exactly — do not report a total.",
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / didYouMean
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / excludedTerms
      Removed value: -{
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • removedOutput schema / properties / filterCoverage
      Removed value: -{
      -  "additionalProperties": {
      -    "type": "number"
      -  },
      -  "description": "For each filter applied, the live share (0-1) of the board that states the field it filters on; rows that state nothing are excluded.",
      -  "type": "object"
      -}
    • removedOutput schema / properties / filterCoverageAt
      Removed value: -{
      -  "description": "When filterCoverage was measured. ABSENT when a figure is a pinned fallback rather than a live reading.",
      -  "type": "string"
      -}
    • removedOutput schema / properties / hasMore
      Removed value: -{
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / ignoredFilters
      Removed value: -{
      -  "description": "Filters the board could NOT apply. Results answer a wider question than was asked.",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • removedOutput schema / properties / intentFilters
      Removed value: -{
      -  "description": "Words read out of the query as filters.",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • removedOutput schema / properties / nextOffset
      Removed value: -{
      -  "description": "Pass back as `offset` for the next page.",
      -  "type": "integer"
      -}
    • removedOutput schema / properties / relatedCapped
      Removed value: -{
      -  "description": "relatedTotal stopped counting at the board's cap; the true figure is higher.",
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / relatedTotal
      Removed value: -{
      -  "description": "Further postings matched in the description only, beyond `total` (which counts title matches). Each card says which in matchScope.",
      -  "type": "integer"
      -}
    • removedOutput schema / properties / results / items / additionalProperties
      Removed value: -true
    • removedOutput schema / properties / results / items / properties / id / description
      Removed value: -"The job id — pass it to fetch, get_job, check_jobs_open."
    • removedOutput schema / properties / results / items / properties / title / description
      Removed value: -"Title and employer, one line."
    • removedOutput schema / properties / salaryStatedOnly
      Removed value: -{
      -  "description": "Row-selecting: this page excludes the postings with no annualised figure in approximate US dollars, including postings that publish an hourly rate (filterCoverage, when present, gives the live share).",
      -  "type": "boolean"
      -}
    • removedOutput schema / properties / total
      Removed value: -{
      -  "description": "Exact match count. ABSENT with countUnavailable:true when the board refuses to guess.",
      -  "type": [
      -    "integer",
      -    "null"
      -  ]
      -}
  2. Changed5 schema fields changed
    • addedOutput schema / properties / filterCoverage
      Added value: +{
      +  "additionalProperties": {
      +    "type": "number"
      +  },
      +  "description": "For each filter applied, the live share (0-1) of the board that states the field it filters on; rows that state nothing are excluded.",
      +  "type": "object"
      +}
    • addedOutput schema / properties / filterCoverageAt
      Added value: +{
      +  "description": "When filterCoverage was measured. ABSENT when a figure is a pinned fallback rather than a live reading.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / relatedCapped
      Added value: +{
      +  "description": "relatedTotal stopped counting at the board's cap; the true figure is higher.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / relatedTotal
      Added value: +{
      +  "description": "Further postings matched in the description only, beyond `total` (which counts title matches). Each card says which in matchScope.",
      +  "type": "integer"
      +}
    • changedOutput schema / properties / salaryStatedOnly / description
      Previous value: -"Row-selecting: this page excludes the ~76% of postings with no annualised figure in approximate US dollars (2026-09-27), including postings that publish an hourly rate."New value: +"Row-selecting: this page excludes the postings with no annualised figure in approximate US dollars, including postings that publish an hourly rate (filterCoverage, when present, gives the live share)."
  3. Changed1 schema field changed
    • changedOutput schema / properties / salaryStatedOnly / description
      Previous value: -"Row-selecting: this page excludes the ~87% of postings with no stated pay."New value: +"Row-selecting: this page excludes the ~76% of postings with no annualised figure in approximate US dollars (2026-09-27), including postings that publish an hourly rate."
  4. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description still adds real behavior beyond them: identical ranking and the same 10-row page as keyless search_jobs, and 'the disclosures ride beside the results.' It stops short of describing pagination limits or what happens when the 10-row page is exhausted, which is the main residual gap.

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-loads the alias relationship and the I/O shape, then the routing rule — good ordering with no filler sentences. Slight redundancy in restating the output shape that the output schema already carries, and 'the disclosures ride beside the results' is evocative but imprecise.

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 an output schema present the description needn't enumerate return fields, yet it usefully explains what id, title and url are for downstream calls. Combined with full schema coverage and annotations, an agent has enough to invoke it correctly; only page-boundary/pagination behavior is unstated.

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 100% and the single query param is fully documented there, including leading-minus exclusions, so the baseline is 3. The description only restates 'one query string in' and adds no syntax or semantic detail beyond 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?

Names the exact verb/resource relationship ('An ALIAS of search_jobs') and pins the contract: 'one query string in, {results:[{id,title,url}]} out.' It distinguishes itself from the sibling search_jobs by audience (ChatGPT deep-research / company-knowledge connectors) rather than leaving the agent to guess.

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?

Explicit routing in both directions: this tool is for the fixed research shape, and 'Any other client should call search_jobs, which takes every filter.' That is an unambiguous when-to-use / when-not-to-use split with the alternative named.

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.