CareerGenius

Interview prep for a job

careergenius_interview_prep

Read-only

Likely interview questions for one job posting, each with an answer outline built ONLY from the resume: every point cites the resume line it comes from and passed the CareerGenius fact check (no invented experience; failing points are removed and listed by reason). Resume as plain text, a PDF/DOCX file (base64) or structured JSON. Counts one call and uses the AI cap. Without a key: one of the conversation's 2 free AI calls (posting_text only; job_url needs a key). Without a key the whole request is limited to 96 KB.

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": {
      "on_behalf_of": "<on_behalf_of>"
    },
    "name": "careergenius_interview_prep"
  }
}

Input Schema

Name	Required	Description
`links`	No
`resume`	No	Structured resume. Only what the person really has done: every output is checked against it.
`contact`	No
`job_url`	No	A public job posting link (Greenhouse, Lever, Ashby, SmartRecruiters, Workday or a page with JobPosting data). Fetched by our job-import engine; private or internal addresses are refused.
`resume_file`	No
`resume_text`	No	A pasted plain-text resume. Read by a fixed layout parser (no AI, nothing added); section headings (Summary, Experience, Education, Skills) help.
`on_behalf_of`	Yes	Required. You confirm a person asked for this, and the resume is theirs (or they are authorised to use it).
`posting_text`	No	The job posting text (preferred).
`idempotency_key`	No	Optional, keyed calls only (ignored without a key). Retrying with the same key returns the first answer and is not charged twice. Only when you send it, that answer (which can contain text taken from the resume) is kept for 24 hours so the retry can be replayed, then deleted. Without it nothing from the request is stored.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Adds real context beyond annotations: outputs are fact-checked against the resume, unsupported points are removed and surfaced with reasons, and quota/key-gated behavior is spelled out. Annotations already declare readOnlyHint=true and openWorldHint=false, and nothing here contradicts them. Remaining gaps: no statement of latency, failure modes when the posting cannot be fetched, or how many questions 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?

Purpose and grounding guarantee are front-loaded, then input formats, then cost/quota. Every sentence carries information, though the trailing parentheticals about free calls and the 96 KB cap make the last two sentences dense and slightly harder to parse on first read.

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?

For a 9-parameter, nested-object, no-output-schema generation tool, the description covers the essential decision inputs: what it returns conceptually, resume source choices, key-gating, and size limits. It does not describe the shape of the returned question/answer-outline payload or the reasons list, which the agent would need to know to consume the result without an output schema.

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 description coverage is 67%, so the schema already carries much of the load. The description does add meaning for the mutually exclusive resume input paths and the key-dependent behavior of job_url and the 96 KB no-key request ceiling. It says nothing about the 5-link array, contact block, or how on_behalf_of is enforced beyond what the schema states.

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?

Opens with a specific verb+resource+scope: 'Likely interview questions for one job posting, each with an answer outline built ONLY from the resume.' The grounding constraint (resume-only, fact-checked, failing points removed and listed by reason) makes the output uniquely distinguishable from sibling tools like cover_letter or tailor_resume without needing to name them.

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 clear operational context: three accepted resume input forms, the free-tier path (posting_text only; job_url needs a key), and that it consumes one AI call against a cap. It does not explicitly say when to prefer this over careergenius_cover_letter or careergenius_tailor_resume, so the agent must infer the routing from purpose alone.

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

All CareerGenius 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?