Skip to main content
Glama

PickedJobs

Save search

save_search
DestructiveIdempotent

Saves a job search to this account, with optional daily or weekly email alerts sent to the account’s verified email address. Saving filters equivalent to an existing saved search updates its name and alert settings instead of adding a duplicate. Accounts can keep up to 100 saved searches. Does not use the job allowance.

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": {
      "name": "<name>"
    },
    "name": "save_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoKeywords matched against job title, company and stack, e.g. "platform engineer".
nameYesName for the saved search, e.g. "Senior Rust, remote Europe".
roleNoOne or more engineering specialties. Implies category engineering.
stackNoOne or more technologies. Matches jobs mentioning any selected technology.
regionNoOne or more regions the candidate can work from.
remoteNoOne or more arrangements: remote, remote_region, hybrid or onsite.
companyNoCompany slug from a previous result's companySlug.
categoryNoKind of role.
salaryMinNoMinimum pay. Only matches jobs that publish salary. Defaults to USD per year.
seniorityNo
employmentNoOne or more employment types. eor: hired through an employer of record.
emailAlertsNoEmail new matching jobs to the account’s verified email. Defaults to false.
postedWithinNoOnly jobs posted in the last N days.
salaryPeriodNo
alertFrequencyNoHow often alert emails are sent. Defaults to daily.
salaryCurrencyNoISO currency code for salaryMin, e.g. USD, EUR, GBP.
visaSponsorshipNoOnly jobs whose posting says the employer sponsors visas. Most postings don't say either way.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Goes beyond the annotations on several fronts: it discloses the deduplication/update behavior (which explains idempotentHint=true), the 100-search account limit, that alerts go to the account's verified email, and that saving does not consume the job allowance. It does not explicitly warn that an existing search's name and alert settings are overwritten, which is the destructive edge implied by destructiveHint=true, so the mutation risk is only partially spelled out.

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?

Four short sentences, front-loaded with the core action, then dedup semantics, then the account cap and quota note. Every sentence carries information an agent cannot get from the schema or annotations.

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 17-parameter mutation with rich enum-documented schema and no output schema, the description covers the behaviors an agent actually needs: upsert semantics, limits, alert delivery, and quota impact. The remaining gap is that it never says what comes back (e.g. a saved search identifier) or how the stored search can later be retrieved or removed.

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 88%, so the schema already carries most parameter meaning and the baseline is 3. The description adds only a little beyond it, tying emailAlerts/alertFrequency to a verified email address and daily/weekly cadence, but says nothing about the filter parameters (q, role, stack, salaryMin, etc.).

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: 'Saves a job search to this account', and adds the upsert rule ('Saving filters equivalent to an existing saved search updates its name and alert settings instead of adding a duplicate'), which tells an agent this is not a plain create. It never names a sibling tool, so differentiation from list_saved_searches or delete_saved_search is left implicit.

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 rather than stated: the agent can infer this is the tool for persisting a search, and the 100-search cap and 'Does not use the job allowance' note give useful preconditions. There is still no explicit when-to-use / when-not-to-use guidance and no routing to alternatives (e.g. list_saved_searches to check for an existing entry before saving).

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