Skip to main content
Glama

track job

track_job

Add a role to the user's pipeline at the Wishlist stage. Given a url, it reads the posting's text from that page, saves it on the role and scores the user's fit once with their AI (the pipeline badge), so tailoring and prep can read the posting. Use it when the user wants to save or track a role; read_page only reads a page, and move_job changes the stage of a role already tracked. A role already in the pipeline is left as it is, apart from gaining missing posting text. It asks the user first, and never applies or contacts the company. Returns the stage, the fit and a link to the role's card. Once it's saved, undo can put it back within 24 hours.

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": {
      "company": "<company>",
      "title": "<title>"
    },
    "name": "track_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoThe posting's full link; its text is read and saved on the role
titleYesThe role's title as the posting gives it, e.g. "Senior Product Manager"
companyYesThe employer's name, e.g. "Stripe"
locationNoWhere the role is, e.g. "Remote" or "New York, NY"; leave empty to take it from the posting

Output Schema

NameRequiredDescriptionDefault
textYesThe answer, or what was done, in plain words for the user: the same text as content
undoNoOn a saved write: its undo handle, for undo within 24 hours
widgetNoThe card the host draws with it, e.g. "pipeline"; "confirm" means a write waits for the user's Yes and nothing is saved yet

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / undo
      Added value: +{
      +  "description": "On a saved write: its undo handle, for undo within 24 hours",
      +  "type": "string"
      +}
  2. Changed5 schema fields changed
    • addedInput schema / properties / company / description
      Added value: +"The employer's name, e.g. \"Stripe\""
    • addedInput schema / properties / location / description
      Added value: +"Where the role is, e.g. \"Remote\" or \"New York, NY\"; leave empty to take it from the posting"
    • addedInput schema / properties / title / description
      Added value: +"The role's title as the posting gives it, e.g. \"Senior Product Manager\""
    • addedInput schema / properties / url / description
      Added value: +"The posting's full link; its text is read and saved on the role"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "additionalProperties": false,
      +  "properties": {
      +    "text": {
      +      "description": "The answer, or what was done, in plain words for the user: the same text as content",
      +      "type": "string"
      +    },
      +    "widget": {
      +      "description": "The card the host draws with it, e.g. \"pipeline\"; \"confirm\" means a write waits for the user's Yes and nothing is saved yet",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "text"
      +  ],
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare the write, open-world, and non-idempotent profile, and the description adds real context on top: user confirmation is requested, the company is never contacted, existing pipeline roles are left intact except for backfilling missing posting text, and undo is available for 24 hours. It does not describe rate limits, failure modes (for example, an unreadable URL), or what happens if the fit score call fails mid-way. Given how much the annotations cover, this is solid but not exhaustive.

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?

The core action and scoping constraint are front-loaded, and the sibling contrast follows immediately. It is longer than needed, with the return-value sentence and 24-hour undo window appended loosely rather than grouped, but nearly every sentence carries information.

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?

For a mutating, open-world tool with a confirmation step and irreversible-by-default semantics, the description covers prerequisites, side effects, the existing-role case, the undo window, and the return contents (stage, fit, card link) even though an output schema exists. Nothing an agent needs in order to call it correctly is missing.

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%, so the schema already documents all four parameters, including how location defaults from the posting. The description adds only a little beyond that: the URL is read for text and stored on the role, which slightly clarifies the url parameter's side effect. Correct baseline for schema-documented parameters.

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 description gives a specific verb and resource (add a role to the pipeline at the Wishlist stage) and adds the side effects: reading the posting's text, saving it, and scoring fit. It also names the siblings it is not (read_page only reads a page; move_job changes the stage of an already-tracked role), so the agent can distinguish it without opening the 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 states explicitly when to use the tool ("when the user wants to save or track a role") and contrasts that with two named alternatives and the conditions under which to choose them. It also specifies the pre-call behavior ("asks the user first"), giving a prerequisite an agent would not otherwise infer.

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