Skip to main content
Glama

Save Job Matches

getmattered_save_matches
Idempotent

Saves job match IDs to your saved list for later review without starting or submitting an application.

Instructions

Saves job matches to the user's saved list for later. Saving starts no application; getmattered_apply applies. getmattered_get_matches with saved_only reads the list, and getmattered_unsave_matches undoes a save. Returns one result per id. Nothing is sent or spent.

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": {
      "job_match_ids": "<job_match_ids>"
    },
    "name": "getmattered_save_matches"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_match_idsYesJob match ids from getmattered_get_matches, 1 to 25 (e.g. [48213, 48214]).

Output Schema

NameRequiredDescriptionDefault
actionYesThe operation that ran, one of save, skip, unsave or restore.
resultsYes
attemptedYes
setupStepNoPresent while account setup is open: the first setup step.
succeededYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.13.2
    • changedOutput schema / properties / action / description
      Previous value: -"The operation that ran: save, skip, unsave or restore."New value: +"The operation that ran, one of save, skip, unsave or restore."
    • addedOutput schema / properties / setupStep
      Added value: +{
      +  "description": "Present while account setup is open: the first setup step.",
      +  "type": "string"
      +}
  2. Addedv1.10.2

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the description does not need to re-state safety. It adds genuinely new context instead: saving does not trigger an application, nothing is sent or spent, and the response contains one result per supplied id. It stops short of describing failure modes or partial-success behavior.

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 with zero filler, front-loaded with the action and immediately followed by the disambiguation clauses. Every sentence carries a distinct fact: purpose, side-effect boundary, alternatives, and return shape.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool takes a single id array and has an output schema, so return values need no explanation here; annotations cover the safety profile. The description closes the remaining gaps an agent could plausibly get wrong: that saving is not applying, that unsaving exists, and that nothing is transmitted or billed.

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% and the schema already documents the id array, its source (getmattered_get_matches), the 1–25 bound and an example. The description adds only the return-shape hint ("one result per id"), which is a light mapping aid rather than new parameter meaning, so the baseline holds.

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?

The first sentence pairs a concrete verb ("Saves") with a concrete resource and destination ("job matches to the user's saved list"). It then explicitly contrasts with getmattered_apply, getmattered_unsave_matches and getmattered_get_matches, so the agent can distinguish it from every nearby sibling without reading a schema.

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?

It names the alternative for each adjacent intent: applying (getmattered_apply), reading the saved list (getmattered_get_matches with saved_only) and reversing (getmattered_unsave_matches). This is explicit when/when-not/alternative routing rather than inferred usage.

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