Skip to main content
Glama

Create resume

create_resume
Destructive

Use this when the person wants to save their resume in CVEmber or build a new one, including from scratch. file: the attached resume file itself (PDF, Word, text, photo); CVEmber reads it. sourceText: pasted text, exactly as pasted. content: a resume built from the person's own answers. Adds a master resume for a role and never changes an existing one; an existing master for the role comes back as duplicate_resume. Do not use only to check a score; score_resume does that without saving.

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
fileNoThe resume file the person attached (PDF, Word, text or a photo), passed as is.
roleNoIn the person's words; read from the resume if omitted.
titleNo
dryRunNoValidate only; nothing is saved.
colorIdNoA colour id, e.g. navy, blue, teal.
contentNo
sourceKindNo
sourceTextNoText the person pasted, copied exactly.
templateIdNoA template id from list_templates.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / file
      Added value: +{
      +  "description": "The resume file the person attached (PDF, Word, text or a photo), passed as is.",
      +  "properties": {
      +    "download_url": {
      +      "description": "Download link of the attached file.",
      +      "type": "string"
      +    },
      +    "file_id": {
      +      "type": "string"
      +    },
      +    "file_name": {
      +      "type": "string"
      +    },
      +    "mime_type": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "download_url",
      +    "file_id"
      +  ],
      +  "type": "object"
      +}
    • changedInput schema / properties / sourceText / description
      Previous value: -"Attached file's text, unedited."New value: +"Text the person pasted, copied exactly."
  2. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
      -  "content"
      -]New value: +[]
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations (readOnly=false, destructive=true, idempotent=false), the description discloses the key side effect: a new master resume is added per role, existing resumes are untouched, and a pre-existing master returns as duplicate_resume. That materially refines the blunt destructiveHint flag. It stops short of describing the success response shape or how content/file/sourceText interact when several are supplied.

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 trigger condition, then a compact field glossary, then the exclusion — each sentence earns its place. The colon-list style for file/sourceText/content is slightly telegraphic but efficient for a nine-parameter tool.

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 nine-parameter tool with nested objects and no output schema, the description covers the hard parts (input mode selection, duplicate behavior, no-mutation guarantee) well. The remaining gap is what a successful call returns and how dryRun output differs, which the agent must infer.

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?

The description adds real meaning to the three source parameters: file is read by CVEmber, sourceText must be verbatim, and content is a resume assembled from the person's own answers — clarifying these as alternative input modes rather than cumulative ones. It says nothing about role, title, sourceKind, or how omitted fields are inferred, though the schema covers several of those at 67% coverage.

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 description opens with a specific verb and resource ('save their resume in CVEmber or build a new one, including from scratch') and immediately contrasts it with the sibling tool that only scores. An agent can distinguish create_resume from score_resume, update_resume, and tailor_resume without opening a schema.

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 gives both the positive trigger ('when the person wants to save their resume... or build a new one') and an explicit exclusion ('Do not use only to check a score; score_resume does that without saving'), naming the alternative. It also clarifies the additive-only case ('never changes an existing one'), which heads off the update path.

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