Skip to main content
Glama
Sign In

ATSPrep

by io.github.Devabubakar
OverviewDiscussionsAdmin

Review an interview answer

review_interview_answer
Read-only

Use this when the user gives an answer to an interview question and wants feedback on it. Review the user's answer to an interview question: a rating, length and speaking time, STAR coverage for stories, filler words, specific checks, the follow-up an interviewer would likely ask, and a stronger version that keeps to the user's own facts. Part of the answer is drafted by an AI model (Gemma 4, with Llama 3.3 70B as a backup, on Cloudflare Workers AI) behind ATSPrep's guard, which drops any figure, name or tool the user's text doesn't contain. If the AI part is unavailable, the rule-based part still comes back and ai.message says why.

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": {
      "question": "<question>",
      "answer": "<answer>"
    },
    "name": "review_interview_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNostory (default: a past example, scored on STAR), pitch (tell me about yourself), plan (how would you…), number (salary or a figure) or close (questions for them).
answerYesThe user's answer, as they would say it.
questionYesThe interview question.
resume_textNoOptional. The resume, so the stronger answer can use real facts from it.

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 already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely new behavioral context: an AI portion drafted by named models behind ATSPrep's guard that drops any figure, name or tool not present in the user's text, plus explicit degradation behavior (rule-based portion still returns and ai.message explains why). This is rare, valuable disclosure of processing pipeline and failure modes.

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 the trigger condition, then a dense but purposeful list of what the review returns, then behavioral notes. Every sentence carries information, though the long enumerated second sentence and model-name detail could be tightened.

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?

With no output schema, the description carries the burden of explaining returns, and it does so thoroughly (rating, timings, STAR coverage, fillers, follow-up question, stronger answer). Combined with the fallback explanation, an agent knows what it will get from the four-parameter call.

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 100%, so the schema already explains each parameter, including the kind enum and the optional resume_text. The description only obliquely touches parameters ('keeps to the user's own facts'), adding little syntax or format meaning beyond the schema, so the baseline 3 applies.

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 uses a specific verb+resource ('Review the user's answer to an interview question') and enumerates exactly what the review contains (rating, length/speaking time, STAR coverage, filler words, likely follow-up, stronger version). This clearly separates it from siblings like interview_questions (which generates questions rather than scoring an answer).

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?

'Use this when the user gives an answer to an interview question and wants feedback on it' states a clear triggering condition. It does not name a competing alternative (e.g., interview_questions for question generation) or any when-not condition, so it stops short of full routing guidance.

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

All ATSPrep toolsInspect
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