Skip to main content
Glama

Edit a resume section

update_resume_section
Destructive

Apply an edit to one section of a resume. Editable sections: full_name, title, contacts, summary, experience, education, skills, projects, languages, interests, publications, references. Two modes, exactly one per call. ops (list sections) makes targeted add/update/remove changes addressed by the entry 'id' from get_resume; entries an op does not name stay untouched. payload replaces the whole section: an entry missing from it is removed; an entry carrying its 'id' from get_resume is matched to the stored one, and within it a key left out keeps its current value. Entry ids belong to the content_version they were read with: a call that names entries by id carries it as expected_content_version, and gets 'resume_changed' when the resume changed since. Returns the edited section with its entry ids and the new content_version; get_resume reads the whole resume. Experience dates are checked on the entries an edit adds or changes: no start in the future, no end before the start, no end date on a current role. Returns 'not_found' if the resume does not exist or does not belong to the current user, and 'invalid_payload' if the edit does not match the section shape.

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": "update_resume_section"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes

Output Schema

NameRequiredDescriptionDefault
idYes
undoNoSet only by an edit that changed something: the versions around it.
styleNoCurrent visual style. Read-only here; change via set_resume_style.
titleNoProfessional title/headline (section: title).
skillsNo
sectionYesThe section this edit changed — the only section included; get_resume reads the rest.
summaryNo
contactsNo
languageNoLocale code the resume content is written in, e.g. en_EN. Not the spoken languages list.
projectsNo
educationNo
full_nameNoPerson's full name (section: full_name).
interestsNo
languagesNo
experienceNo
referencesNo
updated_atNo
resume_nameYesDocument name shown in list_resumes; change it via rename_resume, not update_resume_section.
publicationsNo
content_versionNoContent version of this read: a hash of the content, so equal content gives an equal version, also across copies. Entry ids belong to it; update_resume_section takes it as expected_content_version and answers 'resume_changed' once the resume has changed since.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / $defs / ResumeStyleInfo / properties / font / description
      Added value: +"Font pair: default is Inter (sans-serif) — a chosen font, not an unset one; classic is Lora, modern is Jost."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

The annotations already mark this as a destructive mutation, but the description adds substantial operational detail: payload removes omitted entries, ops leave unnamed entries untouched, ids are tied to content_version, stale versions return 'resume_changed', dates are validated, and specific errors are returned.

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?

The description is front-loaded with purpose, editable sections, and modes before moving into detailed semantics and error behavior. It is dense and somewhat repetitive around section names and payload shapes, but the length is justified by the tool's nested, destructive editing behavior.

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 destructive nested mutation with an output schema, the description covers mode selection, entry identity, version conflicts, date validation, error cases, and return content. An agent has enough context to invoke it safely and correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even with low reported schema description coverage, the description documents the key parameter semantics: exactly one of ops or payload, id requirements for add/update/remove, matching by id or identifying keys, field-clearing rules, expected_content_version, and section-specific payload shapes.

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 the specific action (apply an edit) and resource (one resume section), then names all editable sections and the two mutually exclusive edit modes. It also distinguishes this from get_resume by explaining that get_resume reads the whole resume.

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?

Explains that exactly one of `ops` or `payload` must be used and describes what each mode does: targeted id-based changes versus full-section replacement. The choice between modes is strongly implied by their consequences, although the description does not give explicit 'use ops when... use payload when...' guidance.

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.