Skip to main content
Glama

Analyze a job offer

analyze_offer

Analyse a job offer the user received and draft the negotiation scripts. Takes the offer text exactly as they got it — the recruiter's email, message or their own notes; the numbers are extracted from that wording, so a retold or summarised version loses them. Runs asynchronously: this returns an offer_id immediately, and get_offer(offer_id) shows the verdict, the market comparison and the counter-offer email once done. vacancy_id links the offer to a tracked vacancy. The market is read for where the user lives and how they are hired: pass candidate_country, employer_country and employment_type when the user said them; a left-out country is taken from their profile. Counts as one offer analysis against the user's plan — the free plan allows one a month. Returns 'limit_exceeded' naming the day it frees up when the quota is spent, 'no_resume' when the user has no resume to compare against, 'draft_limit_reached' when too many offers are waiting to be finished, 'not_found' for a foreign vacancy_id, and 'invalid_payload' for empty or oversized text.

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": "analyze_offer"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes

Output Schema

NameRequiredDescriptionDefault
statusNoAlways 'processing' — the analysis runs asynchronously.processing
task_idYesBackground task id (informational; get_offer shows progress).
offer_idYesId of the created offer; pass to get_offer once ready.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false; the description adds substantial context beyond that — quota consumption (one analysis per month on free plan), async execution returning offer_id immediately, and five named failure modes (limit_exceeded, no_resume, draft_limit_reached, not_found, invalid_payload). These are exactly the behavioral traits an agent cannot infer from annotations.

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-loads purpose and the verbatim-input constraint before the async note and error list, which is the right order for an agent. It is dense and the long error-code sentence runs on, but every clause carries operational information.

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 an async, quota-limited analysis tool with a nested input object and an output schema, the description supplies everything needed: how to call it, what comes back immediately, where the results live, and the exact sentinel error strings. Nothing material is left to inference.

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

Parameters3/5

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

The description covers all four nested parameters (source_text, vacancy_id, candidate_country, employer_country, employment_type) in prose, but the meaning it gives is essentially a restatement of the nested schema descriptions, including the profile fallback for a missing country. Complete, but with little added meaning beyond the structured fields.

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 ('analyse a job offer ... draft the negotiation scripts') and goes further by naming the required input shape (offer text as received) and the follow-up tool get_offer(offer_id). An agent can distinguish this from siblings like analyze_vacancy or analyze_radar_match purely from the description, since this one is offer-specific and async with an offer_id handoff.

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 a clear trigger ('a job offer the user received') and prescribes the input form ('takes the offer text exactly as they got it'), plus when to supply the country/employment params versus letting the profile fill in. It does not explicitly compare itself against analyze_vacancy or analyze_tracked_vacancy, so the when-not guidance is only implied.

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.