Skip to main content
Glama

Jobiba Jobs: Job Search, Salary, CV & Apply

Update my profile from my CV

import_profile_from_cv
Destructive

Preferred way to fill the profile from a CV the user shared in chat: send the facts you read in the CV as typed fields. Without apply=true it returns a preview only. Empty profile fields are filled, lists only grow, nothing already on the profile is overwritten (the summary only with replaceSummary=true). With cvText every fact must appear in that text or it is skipped. A job without a start date is skipped and reported: ask the user for it, never guess. Date of birth, gender, marital status and pay are never accepted. The result lists applied, kept and skipped fields with reasons; tell the user exactly that.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "import_profile_from_cv"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity (and region/country) where the user lives, as in the CV.
applyNotrue only after the user approved the preview.
phoneNoPhone number exactly as in the CV.
cvTextNoOptional plain text of the CV. When given, every fact is checked against it and facts not found are skipped.
skillsNo
addressNoPlace line from the CV, e.g. 'Pune, Maharashtra, India'. No street address needed.
summaryNoProfessional summary as written in the CV (or a faithful short version).
educationNo
githubUrlNoGitHub profile link from the CV.
languagesNo
experienceNo
linkedinUrlNoLinkedIn profile link from the CV.
noticePeriodNoNotice period as stated, e.g. '30 days'.
portfolioUrlNoPortfolio / personal site link from the CV.
certificationsNo
replaceSummaryNotrue only when the user asked to replace their current summary.
workPreferenceNoOnly if the CV states it.
interestedRolesNoRoles the user wants next (job titles only).
interestedCitiesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations, explaining the actual merge semantics: empty fields are filled, lists only grow, existing values are preserved except the summary with replaceSummary=true, and cvText turns the call into a grounding check where unverifiable facts are skipped. It also names prohibited fields (date of birth, gender, marital status, pay) and the start-date validation rule with the instruction to ask rather than guess. The remaining gap is that it never reconciles the additive nature with the destructiveHint=true flag, which an agent could read as conflicting.

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

Conciseness5/5

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

Front-loaded with purpose and the preferred-source claim, then ordered from safety gate to merge semantics to validation to output handling. Every sentence carries a distinct rule; none restates the title or the schema.

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 19-parameter mutating tool with no output schema, the description covers the important unknowns: preview-vs-commit, merge safety, grounding validation, and the shape of the result ('applied, kept and skipped fields with reasons'). It does not state a minimum payload despite zero required parameters, and it doesn't say how partial failures are reported.

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 a moderate 68%, and the description adds the meaning the schema can't convey for the risky control parameters: what apply and replaceSummary actually gate, and the enforcement rule behind cvText. Domain constraints on experience.startDate (leave out when unknown, entry is reported back) reinforce the schema note. Aggregate fields such as skills, languages, and interestedCities are left to the schema alone.

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?

States a specific verb and resource ('fill the profile from a CV') and pins down the source precisely ('a CV the user shared in chat'), which cleanly separates it from upload- or text-based siblings without needing to name them. It also declares itself the 'preferred way' for that source, so an agent can route correctly on the first read.

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?

Gives an explicit workflow gate: the default call returns a preview only, and apply=true is allowed only after user approval of that preview. It scopes applicability to chat-shared CVs and imposes a clear when-not on the summary field (replaceSummary=true only on explicit request).

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.