Skip to main content
Glama

TrueInterview

Draft answers to a form's open questions

draft_answers

Draft the candidate's answers to an application form's open questions ("Why do you want to work here?", "Describe a project you led"), from their résumé, the notes they asked an agent to keep (for a connection that may read them) and the posting, one per question in order. Each answer lists what it rests on (context_note when it drew on a note), and needs_candidate marks one that needs a fact only they have. Self-identification, salary, visa, ID and password questions are never answered. Give the questions as the form prints them (up to 15) and exactly one of job_id, application_id, or job_description with company and role. It uses the candidate's monthly writing allowance. Give the answers to the candidate as written, to paste into the form.

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": {
      "questions": "<questions>"
    },
    "name": "draft_answers"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNo
job_idNo
companyNo
questionsYes
instructionNo
application_idNo
job_descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses a refusal policy (self-identification, salary, visa, ID and password questions are never answered), a quota cost ('uses the candidate's monthly writing allowance'), and the shape of each returned answer (grounding sources, context_note attribution, needs_candidate flag). This is consistent with readOnlyHint=false, since consuming an allowance is not a pure read.

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?

Front-loaded with purpose, then refusal policy, then input conventions, then output handling – a sensible order with no filler. It is a single very dense paragraph, though, with clauses like the allowance and the paste instruction packed mid-sentence, which slightly hurts scannability.

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 tool with no output schema, the description supplies both the call contract (one of three identifiers, capped question list) and the return shape (per-answer grounding and needs_candidate), plus a safety policy. The main omission is the optional 'instruction' parameter and any note on what happens at the 15-question or allowance limit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry the parameters, and it does for most of them: the questions array (form-printed, max 15), the mutually exclusive choice among job_id / application_id / job_description, and the need for company and role alongside a raw description. The optional 'instruction' parameter (up to 2000 chars) is never mentioned, leaving one of seven parameters undocumented in both schema and prose.

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?

Opens with a specific verb and resource ('Draft the candidate's answers to an application form's open questions') and grounds it with two concrete example questions. The 'give the answers to the candidate as written, to paste into the form' clause distinguishes it from the sibling that actually saves answers (update_application_answers) without needing to name it.

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?

Gives clear preconditions and input conventions: pass questions 'as the form prints them', up to 15, plus 'exactly one of job_id, application_id, or job_description with company and role'. It also implies a usage boundary by returning drafts for the candidate to paste rather than writing to the form. It does not explicitly name an alternative for persisting answers, so it falls short of a 5.

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