Skip to main content
Glama
zcrossoverz

upwork-mcp

by zcrossoverz
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

analyze_job

Score job opportunities across 5 dimensions to decide whether to apply. Evaluates niche fit, client quality, budget fit, competition, and project clarity. Get a grade, recommendation, and suggested bid to inform proposal decisions.

Instructions

Analyze a job opportunity and score it across 5 dimensions to decide whether to apply.

Scoring breakdown (100 pts max):

  • Niche Fit (30pts): How well the job matches n8n/automation keywords

  • Client Quality (25pts): Rating, total spent, hire rate, location

  • Budget Fit (20pts): Budget vs your target rate, estimated total project value

  • Competition (10pts): Number of existing proposals (fewer = better)

  • Project Clarity (10pts): How well-defined the scope is

  • Red Flag Penalty (-5pts each): Vague scope, low budget signals, no client history

Returns: grade (A+/A/B/C/D/F), recommendation (APPLY NOW/APPLY/CONSIDER/SKIP/AVOID), suggested bid, estimated project value, key selling points, and proposal tips.

RECOMMENDED WORKFLOW:

  1. search_jobs → find candidates

  2. get_job_details → get full info

  3. analyze_job → score and decide

  4. submit_proposal → if grade A or B

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
jobYesFull job data object from get_job_details
my_rateNoYour target hourly rate in USD (defaults to BID_RATE_DEFAULT env var)

Implementation Reference

  • src/tools/analyze-job.ts:333-431 (handler)
    Main handler function analyzeJob() that orchestrates all scoring dimensions (niche fit, client quality, budget fit, competition, project clarity, red flags), computes a total score, assigns a grade (A+ through F), and returns a JobAnalysis with recommendation, suggested bid, selling points, and proposal tips.
    export async function analyzeJob(input: AnalyzeJobInput): Promise<JobAnalysis> {
  const myRate = input.my_rate ?? config.bid.default;
  const job = input.job;

  // Run all scorers
  const nicheFit = scoreNicheFit(job);
  const clientQuality = scoreClientQuality(job.client);
  const budgetFit = scoreBudgetFit(job, myRate);
  const competition = scoreCompetition(job.proposals_count ?? '');
  const projectClarity = scoreProjectClarity(job);
  const redFlags = detectRedFlags(job);

  const rawScore =
    nicheFit.score +
    clientQuality.score +
    budgetFit.score +
    competition.score +
    projectClarity.score;

  const penalty = redFlags.count * Math.abs(WEIGHTS.red_flags);
  const totalScore = Math.max(0, rawScore - penalty);
  const maxScore = WEIGHTS.niche_fit + WEIGHTS.client_quality + WEIGHTS.budget_fit + WEIGHTS.competition + WEIGHTS.project_clarity;
  const pct = (totalScore / maxScore) * 100;

  // Grade
  let grade: JobAnalysis['grade'];
  if (pct >= 90) grade = 'A+';
  else if (pct >= 75) grade = 'A';
  else if (pct >= 60) grade = 'B';
  else if (pct >= 45) grade = 'C';
  else if (pct >= 30) grade = 'D';
  else grade = 'F';

  // Recommendation
  let recommendation: JobAnalysis['recommendation'];
  if (pct >= 80 && redFlags.count === 0) recommendation = 'APPLY NOW';
  else if (pct >= 65) recommendation = 'APPLY';
  else if (pct >= 45) recommendation = 'CONSIDER';
  else if (pct >= 30) recommendation = 'SKIP';
  else recommendation = 'AVOID';

  // Key selling points for this specific job
  const keySellingPoints: string[] = [];
  const text = job.description.toLowerCase();

  if (text.includes('n8n')) keySellingPoints.push('Direct n8n experience — mention specific nodes/workflows');
  if (text.includes('webhook')) keySellingPoints.push('Webhook expertise — show real-time integration examples');
  if (text.includes('api')) keySellingPoints.push('API integration — reference similar REST/GraphQL projects');
  if (text.includes('crm') || text.includes('hubspot') || text.includes('salesforce'))
    keySellingPoints.push('CRM automation — mention lead/deal workflow experience');
  if (text.includes('slack') || text.includes('discord'))
    keySellingPoints.push('Messaging platform automation — notification workflows');
  if (text.includes('google sheet') || text.includes('airtable'))
    keySellingPoints.push('Spreadsheet automation — data sync/reporting workflows');
  if (keySellingPoints.length === 0)
    keySellingPoints.push('Highlight n8n as the right tool for their automation needs');

  // Proposal tips
  const proposalTips: string[] = [
    "Open with THEIR problem, not your bio",
    `Mention ${(job.skills ?? []).slice(0, 3).join(', ') || 'their specific tools'} directly`,
  ];
  if ((job.screening_questions ?? []).length > 0) {
    proposalTips.push(`Answer all ${job.screening_questions!.length} screening questions thoughtfully`);
  }
  if (pct >= 65) proposalTips.push('Include a brief workflow diagram or approach outline');
  if (competition.score < 5) proposalTips.push('High competition — make your opener unique and specific');

  return {
    job_title: job.title,
    job_url: job.url ?? '',
    total_score: totalScore,
    max_score: maxScore,
    grade,
    recommendation,
    breakdown: {
      niche_fit: nicheFit,
      client_quality: clientQuality,
      budget_fit: {
        score: budgetFit.score,
        max: budgetFit.max,
        details: budgetFit.details,
        estimated_value: budgetFit.estimated_value,
      },
      competition,
      project_clarity: projectClarity,
      red_flags: {
        count: redFlags.count,
        penalty,
        flags: redFlags.flags,
      },
    },
    suggested_bid: budgetFit.recommendation,
    estimated_project_value: budgetFit.estimated_value,
    key_selling_points: keySellingPoints,
    proposal_tips: proposalTips,
    risk_factors: redFlags.flags,
  };
}
  • src/tools/analyze-job.ts:5-42 (schema)
    Zod schema (AnalyzeJobSchema) and type (AnalyzeJobInput) defining the input shape: a job object (title, description, budget, client, etc.) and an optional my_rate. Also exports the JobAnalysis output interface (lines 308-331).
    export const AnalyzeJobSchema = z.object({
  job: z
    .object({
      id: z.string().optional(),
      title: z.string(),
      url: z.string().optional(),
      description: z.string(),
      budget: z.string().optional(),
      job_type: z.string().optional(),
      duration: z.string().optional(),
      experience_level: z.string().optional(),
      posted_at: z.string().optional(),
      skills: z.array(z.string()).optional(),
      category: z.string().optional(),
      screening_questions: z.array(z.string()).optional(),
      proposals_count: z.string().optional(),
      connects_required: z.string().optional(),
      client: z
        .object({
          name: z.string().optional(),
          location: z.string().optional(),
          rating: z.string().optional(),
          reviews_count: z.string().optional(),
          jobs_posted: z.string().optional(),
          hire_rate: z.string().optional(),
          total_spent: z.string().optional(),
          member_since: z.string().optional(),
        })
        .optional(),
    })
    .describe('Job data from get_job_details'),
  my_rate: z
    .coerce.number()
    .optional()
    .describe('Your target hourly rate in USD. Defaults to BID_RATE_DEFAULT from config.'),
});

export type AnalyzeJobInput = z.infer<typeof AnalyzeJobSchema>;
  • src/index.ts:201-260 (registration)
    MCP tool registration in the direct (non-gateway) server: tool name 'analyze_job', detailed description, and JSON Schema input definition embedded in the TOOLS array.
      {
    name: 'analyze_job',
    description: `Analyze a job opportunity and score it across 5 dimensions to decide whether to apply.

Scoring breakdown (100 pts max):
- Niche Fit (30pts): How well the job matches n8n/automation keywords
- Client Quality (25pts): Rating, total spent, hire rate, location
- Budget Fit (20pts): Budget vs your target rate, estimated total project value
- Competition (10pts): Number of existing proposals (fewer = better)
- Project Clarity (10pts): How well-defined the scope is
- Red Flag Penalty (-5pts each): Vague scope, low budget signals, no client history

Returns: grade (A+/A/B/C/D/F), recommendation (APPLY NOW/APPLY/CONSIDER/SKIP/AVOID),
suggested bid, estimated project value, key selling points, and proposal tips.

RECOMMENDED WORKFLOW:
1. search_jobs → find candidates
2. get_job_details → get full info
3. analyze_job → score and decide
4. submit_proposal → if grade A or B`,
    inputSchema: {
      type: 'object',
      properties: {
        job: {
          type: 'object',
          description: 'Full job data object from get_job_details',
          properties: {
            title: { type: 'string' },
            description: { type: 'string' },
            url: { type: 'string' },
            budget: { type: 'string' },
            job_type: { type: 'string' },
            duration: { type: 'string' },
            experience_level: { type: 'string' },
            skills: { type: 'array', items: { type: 'string' } },
            proposals_count: { type: 'string' },
            screening_questions: { type: 'array', items: { type: 'string' } },
            client: {
              type: 'object',
              properties: {
                rating: { type: 'string' },
                total_spent: { type: 'string' },
                hire_rate: { type: 'string' },
                reviews_count: { type: 'string' },
                jobs_posted: { type: 'string' },
                location: { type: 'string' },
                member_since: { type: 'string' },
              },
            },
          },
          required: ['title', 'description'],
        },
        my_rate: {
          type: 'number',
          description: 'Your target hourly rate in USD (defaults to BID_RATE_DEFAULT env var)',
        },
      },
      required: ['job'],
    },
  },
  • src/index.ts:328-332 (registration)
    CallToolRequestSchema handler switch case: validates args with AnalyzeJobSchema.parse() and calls analyzeJob() in the direct server mode.
    case 'analyze_job': {
  const input = AnalyzeJobSchema.parse(args);
  result = await analyzeJob(input);
  break;
}
  • src/gateway.ts:147-161 (registration)
    Gateway-mode registration: tool name 'analyze_job' with inputSchema and description. The actual execution is proxied to the worker (line 177 via callWorker).
      {
    name: 'analyze_job',
    description: `Score a job opportunity 0-100 across 5 dimensions: niche fit, client quality, budget fit, competition, clarity.
Returns grade (A+/A/B/C/D/F), recommendation (APPLY NOW / APPLY / CONSIDER / SKIP / AVOID), suggested bid, selling points.`,
    inputSchema: {
      type: 'object',
      properties: {
        job: {
          description: 'Job object with title, description, budget, skills, client info',
        },
        my_rate: { type: ['number', 'string'] },
      },
      required: ['job'],
    },
  },

Tool Definition Quality

A4.5/5.0
Behavior4/5

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

No annotations provided, so description carries full burden. It details scoring dimensions, return values, and workflow. However, it does not explicitly state read-only nature or any side effects, but inference suggests no mutation.

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?

Well-structured with bullet points and workflow, but somewhat lengthy. Every sentence adds value, though could be slightly more concise.

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?

Given nested input and no output schema, description covers scoring, output format, and workflow comprehensively. Could include example grades, but overall sufficient.

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?

Input schema has 100% description coverage, but description adds meaning: job object should come from get_job_details, and my_rate defaults to env var. This enhances understanding beyond schema.

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 clearly states the tool analyzes a job and scores it across 5 dimensions, with a specific scoring breakdown and return values (grade, recommendation, etc.). It distinguishes from siblings like get_job_details (raw details) and submit_proposal (acting on decision).

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 provides a recommended workflow: use after get_job_details and before submit_proposal, and only for grades A or B. This guides when to use and when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zcrossoverz/upwork-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server