Skip to main content
Glama

Create the first resume profile

create_profile

Create the first resume of an account that has no profile yet, either from the text of the user's resume (resume_text) or from five answers about their work (guided: role, years of experience, education, skills, last job). Given both, resume_text is used and guided is ignored. It works before setup is finished and completes setup once the resume is saved. Runs asynchronously — returns a task_id immediately; get_task_status(task_id) reports progress and, when done, the new resume_id. Consumes one resume generation from the user's plan; on the free plan this is the month's only resume generation. Once the resume is saved, the job radar's automatic search is turned on and its first scan runs, built from the resume and the account's country; the account's first scan is not counted against the radar quota. get_radar_status shows the search, and set_radar_auto_search turns it off. The profile's name is the account's name. Guided answers without last_job leave the experience section empty. language defaults to the account's language and is one of: en_EN, ru_RU, es_ES, pt_BR, de_DE, fr_FR, it_IT, tr_TR, hi_IN, uk_UA, id_ID, ja_JP. Returns 'already_set_up' if the account already has a profile, 'limit_exceeded' naming the day it frees up if the plan quota is reached, and 'invalid_payload' when neither input is given or the language code is unknown.

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": {
      "input": "<input>"
    },
    "name": "create_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes

Output Schema

NameRequiredDescriptionDefault
statusYes'processing' — the generation has started; 'already_processing' — one was already running and this is its task.
task_idYesBackground task id; get_task_status reports the new resume_id when it is done.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / $defs / CreateProfileInput / properties / language / description
      Previous value: -"Locale code of the language the profile is written in, e.g. 'en_EN', 'de_DE'. Defaults to the user's language."New value: +"The language the profile is written in: a locale code ('de_DE'), a language code ('de', 'en_US') or its English name ('German'). Defaults to the user's language."
    • changedInput schema / $defs / GuidedProfileInput / properties / role / description
      Previous value: -"The job the user does or is looking for, in their own words."New value: +"The job the user does now or did last, in their own words — not the one they are looking for."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the write/non-idempotent/non-open-world profile; the description adds the traits that actually change agent behavior: the call is asynchronous and returns a task_id, resuming it requires get_task_status, it consumes a plan quota (with a specific free-plan consequence), and it has a side effect of enabling the radar auto search plus running an uncounted first scan. It also discloses failure modes ('already_set_up', 'limit_exceeded' with the freeing date, 'invalid_payload') and the edge case that guided answers without last_job yield an empty experience section.

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?

It is a long description, but it is front-loaded with purpose and precedence before the operational details, and nearly every sentence carries decision-relevant information (async, quota, side effects, error strings). The radar follow-up detail is slightly over-extended for a create call but is defensible as a disclosed side effect.

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 nested, quota-consuming, asynchronous mutation with downstream side effects, the description covers timing, cost, side effects, follow-up calls, and failure codes. An output schema exists, so it does not need to enumerate success return fields, and it doesn't.

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?

Reported schema coverage is 0% at the top level, so the description must compensate, and it does: it names resume_text and the five guided answers (role, years, education, skills, last job), states which wins on conflict, and gives the default and the accepted language codes. It loses a point because its enumerated language list (14 underscore locales) is narrower than the schema, which also accepts bare language codes and English names, leaving a mild mismatch an agent could trip on.

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 first sentence states a specific verb and resource (create the first resume of an account with no profile) and scopes it to first-time creation, which separates it from create_resume_version, rename_resume, and update_resume_section. The two input modes and their precedence are named in the same sentence.

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 the precondition explicitly ('an account that has no profile yet'), the precedence rule when both inputs are supplied ('resume_text is used and guided is ignored'), and the 'already_set_up' outcome if the precondition fails. It also routes the agent to the correct follow-up tools: get_task_status for completion, get_radar_status for the search, set_radar_auto_search to turn it off.

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.