Skip to main content
Glama

VeritaHire live jobs

Report a form question or form behaviour VeritaHire has not seen

report_form_question

Any assistant: when an employer's application form asks a question not in the person's answers, or behaves in a way worth knowing (a field that keeps only digits, a parser that drops job titles), report it here so the next applicant is ready. Send the question as the form prints it and its options - never the person's answer.

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": {
      "text": "<text>"
    },
    "name": "report_form_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
atsNoe.g. Workday, iCIMS, Greenhouse, UKG, NEOGOV, Ashby
kindNoquestion
textYesThe question as printed, or the behaviour seen
optionsNo
employerNo
access_tokenNoNot needed when the person signed in through your Connect / sign-in button (OAuth). Otherwise the access_token from finish_connecting.
suggested_keyNoThe get_my_answers key it matches, if any

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / access_token / description
      Previous value: -"Optional"New value: +"Not needed when the person signed in through your Connect / sign-in button (OAuth). Otherwise the access_token from finish_connecting."
  2. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare this is not read-only and not destructive; the description adds genuinely useful behavior the annotations cannot express: a hard privacy rule ("never the person's answer") and the requirement to send the question verbatim with its options. What is missing is what happens to a submitted report — no mention of deduplication, review, or any confirmation, which matters given idempotentHint=false.

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?

Two sentences, well front-loaded: the audience and trigger come first, then the payload and the privacy constraint. The parenthetical examples earn their place, though the second sentence is heavily compounded and the "Any assistant:" prefix is slightly awkward framing.

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 7-parameter submission tool with no output schema, the description covers who should call it, when, what to send, and the critical privacy boundary. It stops short of describing the outcome of a submission or how duplicates are handled, which is the main remaining gap for a non-idempotent write.

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 around 57%, and the schema already documents ats, kind, access_token and suggested_key. The description adds real meaning for the two remaining key fields by specifying that text must be the question as printed (or the behaviour seen) and that options carries the answer choices — but it says nothing about employer or about how suggested_key should be derived, so it only partly compensates for the coverage gap.

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 description names a specific verb and resource ("report" a "form question" or "form behaviour") and narrows scope to things not already covered ("not in the person's answers", "has not seen"). It is clear what the tool does, but it never distinguishes itself from the closest sibling, report_problem, so an agent must infer that one is for generic problems and this one for unseen form questions/behaviours.

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?

It gives a concrete trigger condition — an application form asks a question not in the person's answers, or behaves oddly (digits-only field, dropped job titles) — with illustrative examples that make the intended moment of use obvious. There is no explicit when-not guidance and no alternative tool is named, which keeps it out of 5 territory.

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