Skip to main content
Glama

Suggest resume changes for a job

request_vacancy_resume_suggestions

Generate structured resume-improvement suggestions tailored to a vacancy analysis. Runs asynchronously — this returns a task_id immediately; poll get_vacancy_detail(vacancy_id) and read 'resume_suggestions' for the completed list. The suggestions also appear in the web UI's vacancy analysis page. Counts as one resume-suggestions action against the user's plan. At a match of 90% or more no suggestions are generated and nothing is spent; the finished task then says skipped: 'high_match' in get_task_status. Returns 'not_found' if the vacancy does not belong to the current user, 'limit_exceeded' naming the day it frees up if the plan quota is reached.

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": "request_vacancy_resume_suggestions"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes

Output Schema

NameRequiredDescriptionDefault
statusNoAlways 'processing' — the job runs asynchronously.processing
task_idYesBackground task id (informational; get_vacancy_detail shows progress).
vacancy_idYesId of the vacancy analysis the task operates on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Excellent disclosure beyond annotations: asynchronous execution returning a task_id, the polling target, quota consumption ('counts as one resume-suggestions action'), the 90% match no-op with skipped: 'high_match' in get_task_status and no spend. It also names error semantics ('not_found' for another user's vacancy, 'limit_exceeded' naming the day quota frees up), all consistent with readOnlyHint=false and idempotentHint=false.

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 purpose, then async mechanics, then cost and edge cases in a logical order with no filler sentences. The web UI mention is marginally useful but not essential, keeping it just short of fully tight.

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?

Covers everything an agent needs despite the output schema: that the immediate return is only a task_id, where the real results land, how to interpret the skip case, and what each failure mode means. Nothing material is left for the agent to 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?

Only one parameter, and the description adds real meaning the schema lacks: the vacancy must belong to the current user (else 'not_found') and the same vacancy_id is used to poll results. Beyond that, little about the id's format is added, but the single-parameter surface needs little more.

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+resource ('Generate structured resume-improvement suggestions') scoped to a vacancy analysis, making clear this is a generation request rather than a read. The async/task_id framing further separates it from retrieval siblings like get_resume_suggestions.

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?

It gives strong when-to-use context: call this to produce suggestions, then poll get_vacancy_detail for 'resume_suggestions', and it explains the automatic skip at >=90% match so the agent knows not to expect output. It does not mention the sibling get_resume_suggestions as an alternate retrieval path, leaving a small routing ambiguity.

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.