Skip to main content
Glama

Worklittle Jobs

Jobs · Create Resume

create_resume
Destructive

Jobs — Write a one-page resume for the user from what they tell you (work history, skills, education) or their saved profile, fitted to a job when job_id is given. Never invent facts. When details are thin, pass draft true and fill the [ ] gaps with them. When it is their new or updated main resume, pass save_to_profile true to save it to their profile in the same call (ask first; it replaces the current main resume). Costs $0.01.

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": "create_resume"
  }
}

Input Schema

NameRequiredDescriptionDefault
draftNotrue: a draft that keeps [ ] gaps for missing facts instead of failing on thin input. Same price. Can't be saved.
formatNohtml | pdf | docx. pdf/docx also include html. Prefer formats[] when requesting multiple.
job_idNo
formatsNoSubset of html, pdf, docx. Default when omitted: html and pdf.
profileNo
job_contextNo
resume_textNoWhat the user told you or their old resume, as plain text.
instructionsNo
save_to_profileNotrue: save the finished PDF as the user's main resume, so applications send it. Not with draft.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations flag destructiveHint=true, and the description earns that by explaining exactly what is destroyed: save_to_profile replaces the current main resume, so the agent is told to ask first. It also discloses cost ($0.01, with draft at the same price), the hard incompatibility between draft and save_to_profile, and the anti-invention constraint — all behavior not present in structured fields.

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?

Three dense sentences, front-loaded with the core action before the conditional modifiers, and every clause carries operationally useful information. It is slightly compressed into run-on phrasing (parentheticals, multiple 'when' clauses) but there is no filler.

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 9-param, nested-object, paid mutation tool with an output schema, the description covers the decision-critical facts: cost, destructive replacement semantics, draft vs. save exclusivity, and no-fabrication behavior. Gaps are limited to the shape of the profile/job_context objects and format selection, which the schema largely handles.

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 56% schema coverage, the description carries meaningful extra meaning for the highest-stakes params: job_id means 'fit to this job', draft means keep [ ] gaps rather than fail, and save_to_profile means persist as the main resume sent with applications. The remaining params (format/formats, profile, job_context, instructions) rely on the schema, and defaults are only partially echoed via 'Default when omitted' in the schema itself.

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 — 'Write a one-page resume' — with detailed input sources (told details, saved profile, job_id targeting), which clearly separates it from siblings like upload_my_resume, get_my_resume, and delete_my_resume. An agent can identify the tool and its scope from the first clause alone.

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 concrete routing conditions: use job_id when tailoring to a job, pass draft true when details are thin, pass save_to_profile true for a new or updated main resume — and adds a process instruction ('ask first') before that call. It does not explicitly exclude or name alternative tools (e.g., upload_my_resume for an existing file), so it falls short of a full when/when-not map.

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