Skip to main content
Glama

searchnapply

This connector has been deprecated

Replaced by searchnapply.

Deprecated.

Create a job monitor

monitor_create
Idempotent

Purpose: Save a search as a monitor that keeps collecting matching job postings for the user; a title and one real location are required. When: Only when the user asks to be kept informed about a search, with datePosted narrowing the start to recent postings. Cost: About 160 tokens for the saved monitor.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "locations": [
        "Austin, TX"
      ],
      "titleText": "QA engineer",
      "department": "software-it",
      "experience": {
        "exact": "Senior"
      },
      "includeFamily": false
    },
    "name": "monitor_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
keywordsNoWords that must appear in the posting's text.
companiesNoCompany names; a posting from any of them is kept, and leaving them out watches the whole market.
locationsYesReal location names, each read as the closest known location; check monitor.locations in the result for what it watches.
salaryMaxNoHighest yearly salary to keep, in US dollars after the same conversion.
salaryMinNoLowest yearly salary to keep, in US dollars after each posting's published salary is converted.
titleTextYesWords of the job title, matched to one of searchnapply's known roles (resolvedRole.display names it), which the monitor then watches.
datePostedNoHow recently the posting was published; leave it out for any date.
departmentNoOne department slug, to narrow a title that spans departments; call job_postings_search_fields for what each one holds.
experienceNoExperience level to keep, given as exact, since a monitor keeps one level and no lowest level.
includeFamilyNoAlso return postings from the resolved role's wider family; false, the default, keeps the exact role only.
locationTypesNoWorkplace types to keep.
employmentTypeNoEmployment type to keep.
salaryCurrencyNoA three-letter currency code that only labels the monitor.
excludeKeywordsNoWords that must not appear in the title or the text, 1 to 10 words.
includeNoSalaryNoKeep postings that publish no salary; true by default.

Output Schema

NameRequiredDescriptionDefault
monitorYesThe monitor as saved.
titleNoteNoPresent when no role matched: the title words are matched against posting titles.
resolvedRoleNoThe role the title words were read as; absent when no role matched.
unrecognizedLocationsNoThe location names that matched no known location and were left out.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / locations / description
      Previous value: -"Real location names in plain words, each read as the closest known location, so check monitor.locations in the result for what it watches."New value: +"Real location names, each read as the closest known location; check monitor.locations in the result for what it watches."
    • changedInput schema / properties / titleText / description
      Previous value: -"Words of the job title, matched to one of searchnapply's known roles when one fits (resolvedRole.display names it), which the monitor then watches, and otherwise matched against posting titles."New value: +"Words of the job title, matched to one of searchnapply's known roles (resolvedRole.display names it), which the monitor then watches."
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is covered; the description adds the useful ongoing-collection framing and a token cost estimate. However it never explains what idempotentHint=true means in practice for a duplicate create, nor whether there is a cap on monitors. With a rich output schema present, return values correctly don't need describing, so this is a modest but real gap.

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 labeled lines — Purpose, When, Cost — front-load the definition, the trigger, and the budget, with no filler. Every sentence carries information an agent would otherwise have to infer.

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 write tool with a nested object, annotations and a full output schema, the description covers the essentials: what is created, when to create it, which fields are mandatory, and the cost. It is not fully complete on lifecycle behavior (duplicate creates, monitor limits, what happens to an existing similar monitor), but the surrounding structured data carries most of the remaining load.

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 the schema already documents all 15 parameters including the nested experience object; baseline 3 applies. The description adds only the requiredness of title and a "real location", which is already encoded in the required list. The phrase "datePosted narrowing the start to recent postings" reads slightly differently from the schema's recency filter, but the schema remains the authoritative source.

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?

"Save a search as a monitor that keeps collecting matching job postings" names a concrete verb plus resource and makes the persistent/ongoing nature explicit, which separates it from one-off searches. It also states the required inputs. It stops short of naming a sibling (e.g. monitor_update for changing an existing monitor), so differentiation is implied rather than stated.

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?

The "When:" line gives an explicit trigger ("only when the user asks to be kept informed about a search") plus a scoping hint for datePosted. The restrictive "Only when" functions as a when-not guard. What is missing is the named alternative for the adjacent case — e.g. use job_postings_search for a one-off search, or monitor_update for an existing monitor.

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