CareerProAI

careerpro_pack_get

Read-onlyIdempotent

Everything needed to apply: posting text, screen verdict with evidence, tailored resume text, cover letter, pre-mapped answers from your approved answer bank, unanswered questions, dedupe receipt and the per-ATS mode (submit, fill_only, headed, skip). Builds the pack when it does not exist yet; tailoring uses only facts from your own resume. Pricing: {"unit": "call", "price_usd": 0, "free_quota": "200 per day per IP", "note": "Keyed volume pricing is published at https://careerpro.tech/pricing.json"}.

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": {
      "job_id": "<job_id>"
    },
    "name": "careerpro_pack_get"
  }
}

Input Schema

Name	Required	Description	Default
`ai`	No	ai
`job_id`	Yes	job_id

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

B3.2/5.0

Behavior2/5

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

The description adds genuinely useful behavior — the per-ATS mode values (submit, fill_only, headed, skip), the answer-bank sourcing, the dedupe receipt, and that tailoring only uses facts from the user's own resume. However, 'Builds the pack when it does not exist yet' describes a state-changing creation step while annotations declare readOnlyHint=true, which is a real inconsistency an agent should know about.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The return-contents inventory is front-loaded and useful, but the trailing pricing JSON object is verbose clutter for a single-call definition and distracts from the operational description. The first sentence is an undifferentiated list rather than being ordered by decision value.

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?

With no output schema, the description carries the burden of describing what comes back and does so thoroughly, including side effects (pack creation), sourcing constraints (own resume only), and ATS handling modes. The remaining gaps are the meaning of the 'ai' parameter and behavior when no pack can be produced.

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?

Schema coverage is nominally 100%, so the documented-baseline of 3 applies (0 params would be 4). In practice the schema descriptions are vacuous restatements ('ai', 'job_id'), and the tool description explains neither what the 'ai' parameter selects nor what happens with an unknown job_id, so no meaning is added beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete artifact set (posting text, screen verdict with evidence, tailored resume, cover letter, pre-mapped answers, dedupe receipt, per-ATS mode) and states that it builds the pack on demand. That is specific enough to distinguish this aggregate 'pack' tool from the narrower siblings like careerpro_resume_get or careerpro_letter_get, though it never explicitly says it supersedes them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'Everything needed to apply' and 'Builds the pack when it does not exist yet' — an agent can infer this is the one-stop call for an application. There is no explicit when-to-use versus the per-artifact siblings, no guidance on when to prefer the cheaper single-artifact tools, and no stated preconditions beyond job_id.

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

All CareerProAI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?