Skip to main content
Glama

Spanish Top Tech Companies

One posting's application form

job_questions
Read-only

The application form of one posting from find_jobs, read live from its board (Greenhouse, Lever, Ashby, Workable, Recruitee, Teamtailor, BambooHR, Pinpoint, Rippling, Bending Spoons and Eightfold; for Workday, whose form needs the person's account, the posting and Workday's standard steps, also when a Phenom career site leads to it; for SmartRecruiters, the posting only; for SuccessFactors (Capgemini too) and Amazon, the posting and account_required, since their form is shown after sign-in; for careers sites with schema.org JobPosting, the posting; other boards are read in the browser): each question with its type, options, whether it is required, the most characters the board takes (max_length) when it says, and who answers it (person or agent), the posting text marked as untrusted, and the URL to apply at.

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": {
      "id": "<id>"
    },
    "name": "job_questions"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesA job id from find_jobs, e.g. greenhouse:cabify:1234567.
contextNoWhy are you calling this tool? Describe the goal in general terms, and refer to people by role ("a candidate") rather than by name. Leave out personal and identifying information.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Beyond readOnlyHint/openWorldHint, the description discloses that data is read live from the board, that the posting text is marked untrusted (a meaningful prompt-injection signal), that some boards require an account and return account_required instead of a form, and that other boards are read via a browser. These are genuinely useful behavioral traits; only the return-format/pagination details are absent, and the output shape is described instead.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first clause, which is good, but the sentence then expands into an exhaustive board list (eleven named vendors plus Workday, Phenom, SmartRecruiters, SuccessFactors, Amazon) that is mostly noise for tool selection. The return-value summary at the end is valuable and could have been its own short sentence.

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 no output schema, the description usefully enumerates what comes back: question type, options, required flag, max_length, who answers (person or agent), marked untrusted posting text, and the apply URL. For a two-parameter read tool with readOnly/openWorld annotations, that covers what an agent needs to call and interpret the result.

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% for both id and context, so the schema already carries parameter meaning. The description reinforces that the id is a find_jobs job id and introduces account_required as a board-specific outcome, but adds no syntax or format detail beyond the schema.

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?

The opening clause names a concrete resource (the application form of one posting) and its source (find_jobs, read live from the board), which is enough to distinguish it from find_jobs, application_guide, and report_application. The value is muddied by a 90-word parenthetical enumerating boards, but the core verb+resource is unambiguous.

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 id must come from find_jobs, and per-board conditions (Workday/Phenom needing the person's account, SmartRecruiters posting-only, SuccessFactors/Amazon returning account_required) tell an agent what extra context each case needs. There is no explicit when-not-to-use guidance or pointer to application_guide for the next step, so the agent must infer the workflow.

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.