Skip to main content
Glama

HR: Create form

hr_create_form

Create an HR form (a questionnaire). 'kind' is a CLOSED vocabulary — candidate, intern_brief, mentor_review, interview_scorecard, exit, documents, other — and defaults to 'other'. There is no 'survey' value: inventing one is refused, which is the single most common way this call is lost. The form is created together with its first DRAFT version, because a form with no version can be neither edited nor published; the result reports that version as 'draft_version_id'. Nobody can be SENT it until the questions are added and the version is published with hr_publish_form_version — this call alone produces an empty, unsendable form. 'key' is a per-workspace unique slug used by integrations; leave it out and it is generated from the name (Cyrillic transliterated). A key already taken in this workspace is refused rather than silently suffixed. Requires confirmation. CONFIRMATION: this tool is PROPOSED, never performed directly. You get status='confirmation_required' with an action_id and a plan_token, and the write happens only after confirm_action.

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": {
      "name": "<name>"
    },
    "name": "hr_create_form"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNo
kindNo
nameYes
descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Far exceeds the annotations: annotations only say this is a non-read-only, non-destructive, closed-world write. The description discloses the two-phase confirmation protocol (status='confirmation_required', action_id, plan_token, then confirm_action), the side effect of auto-creating a DRAFT version returned as 'draft_version_id', and refusal semantics for enum and key collisions.

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 the resource, then the risky enum constraint, then lifecycle, then confirmation. It is dense but almost every clause carries operational information; the mild redundancy of 'Requires confirmation.' immediately followed by 'CONFIRMATION:' is the only waste.

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?

There is no output schema, and the description fills that gap by naming the returned 'draft_version_id'. For a mutation with four parameters, a hidden side effect, and a deferred-execution protocol, nothing an agent needs 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.

Parameters4/5

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

With schema description coverage at 0%, the description compensates heavily: it enumerates the closed 'kind' vocabulary with its default and the refusal behavior, and explains 'key' as a per-workspace unique slug that is auto-generated from the name with Cyrillic transliteration. Only the 'description' parameter and the length limits go unmentioned.

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, 'Create an HR form', and immediately disambiguates the resource as a questionnaire. It also distinguishes the call from the closely related hr_publish_form_version by stating that this call alone produces an unsendable form.

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?

Explicitly states the downstream condition for usefulness ('nobody can be SENT it until the questions are added and the version is published with hr_publish_form_version') and names the exact sibling to use next. It also gives an enumeration caveat that steers the agent away from inventing values.

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