Skip to main content
Glama

Edit resume

update_resume
Destructive

Use this when the person asks for a change to a saved resume, or tells you something about themselves to add: a job, title, degree, award, skill, language or number. Call it straight away with their exact words in userStatedFacts; that field alone is enough and CVEmber places it on the resume. Do not ask for more details first, do not ask whether it is true, and do not reword it or add entries of your own. resumeId is optional: without it CVEmber uses the resume the person worked on last and names it in the reply. Also use this to remove or reword something, switch template or colour, or rename the resume. expectedVersion is optional. Returns the changes made. restore_version undoes it.

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": "update_resume"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNo
titleNo
colorIdNoA colour id, e.g. navy, blue, teal.
resumeIdNoOptional. Leave it out when the person did not name a resume; CVEmber then uses the resume they worked on last.
sectionsNo
templateIdNoA template id from list_templates.
expectedVersionNocontentVersion from get_resume. Refused if the resume changed since.
userStatedFactsNoWhat the person said about themselves, in their exact words. One string or a list of strings. Example: "I have a PhD from Stanford."

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / resumeId / description
      Previous value: -"A resume id from list_resumes."New value: +"Optional. Leave it out when the person did not name a resume; CVEmber then uses the resume they worked on last."
    • changedInput schema / properties / userStatedFacts / description
      Previous value: -"Person's words; facts need {questionId, text}."New value: +"What the person said about themselves, in their exact words. One string or a list of strings. Example: \"I have a PhD from Stanford.\""
    • removedInput schema / required
      Removed value: -[
      -  "resumeId",
      -  "expectedVersion"
      -]
  2. Changed2 schema fields changed
    • removedInput schema / properties / expectedVersion / maximum
      Removed value: -9007199254740991
    • removedInput schema / properties / expectedVersion / minimum
      Removed value: -0
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds real context beyond them: that omitted resumeId falls back to the last-worked-on resume and is named in the reply, that the tool returns the changes made, and that restore_version can undo the edit. It does not spell out that existing section content may be overwritten by the edit, which is the main residual gap for a destructive operation.

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 the imperative instructions, then the optional-parameter and return details. Dense but nearly all of it earns its place; the repeated emphatics about not rewording and not adding entries restate the same constraint twice.

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 an 8-parameter destructive mutation with nested objects and no output schema, the description covers triggers, defaults, return behaviour, and reversal. The nested sections/role parameters are left to the schema, which is reasonable given 63% schema coverage, but an agent gets no prose guidance on when to populate structured sections versus free-text facts.

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?

Adds substantial meaning to the two most consequential parameters: userStatedFacts is described as sufficient on its own, verbatim, and auto-placed by CVEmber; resumeId's fallback behaviour is stated. Template, colour, and rename intents are mapped to templateId/colorId/title, though the large nested sections object and role are never explained in prose.

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 (edit a saved resume) and enumerates the concrete content it covers: jobs, titles, degrees, awards, skills, languages, numbers, plus template/colour/rename. It also names the sibling that reverses it (restore_version), so the agent can distinguish it from restore_version or create_resume without opening any 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?

Explicitly prescribes when to call (person asks for a change or volunteers a fact about themselves) and gives negative guidance: do not ask for more details first, do not verify truth, do not reword or add entries. It names the alternative for undoing (restore_version) and explains the default path when resumeId is omitted.

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