Semata

Prepare interview questions

prepare_interview_questions

Prepare and save interview questions by candidate application and round, using the CV, role criteria, and current earlier interview evidence. Prepared sets are plans, not proof questions were asked. Pass round when named, focus for time limits or topics, and includeRoleCriteria false for a role-agnostic set. Requires OAuth or a scoped token.

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": {
      "workspaceId": "<workspaceId>",
      "candidateId": "<candidateId>"
    },
    "name": "prepare_interview_questions"
  }
}

Input Schema

Name	Required	Description
`focus`	No	What to emphasise, in the interviewer's words, such as "45-minute technical screen".
`round`	No	The round the interviewer named; omit when unspecified.
`candidateId`	Yes	The candidate id, from list_candidates.
`workspaceId`	Yes	The workspace id returned by list_workspaces. Use 'personal' for the personal workspace.
`includeRoleCriteria`	No	Whether to add a role-fit section from the candidate's role criteria.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations declare this is a non-read, non-destructive, closed-world mutation, and the description adds real context beyond that: the output is a persisted plan rather than a guarantee, and access requires OAuth or a scoped token. It stops short of describing overwrite behavior or whether repeat calls create additional sets.

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?

Four tight sentences, front-loaded with the core action and with the caveat about plans-vs-proof immediately following. Dense but every clause carries information; minor risk of reading as a run-on in the middle.

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 five-parameter mutation with no output schema, it covers inputs, auth requirement, and the nature of the persisted result. The remaining gap is what exactly is returned/stored (set id, question count) and how it interacts with existing question sets.

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?

Schema coverage is already 100%, so the baseline is 3, but the description adds intent-level meaning: round is conditional (only when named), focus carries time limits/topics in the interviewer's words, and includeRoleCriteria=false flips the set to role-agnostic. That is genuine semantic framing rather than restatement.

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 pair ('Prepare and save') plus the resource ('interview questions') and the inputs it draws on (CV, role criteria, earlier interview evidence). It clearly separates itself from retrieval siblings like get_saved_interview_questions and list_interview_question_sets by emphasizing generation plus persistence.

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?

It gives conditional parameter guidance ('Pass round when named', 'includeRoleCriteria false for a role-agnostic set') and clarifies prepared sets are plans, not records of asked questions. However, it never states when to call this versus the sibling read tools, nor any prerequisite ordering beyond a candidateId from list_candidates.

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

All Semata 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?