Skip to main content
Glama

Aethel: AI interview facts and free practice

One question answered company by company

compare_across_companies
Read-onlyIdempotent

One question, answered for every company whose own pages say: who runs the interview (an AI or a person), whether it is recorded, whether it can be retaken, or how long it is. Each row has the company page it rests on and the day it was read; companies whose pages do not say are listed as not known.

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>"
    },
    "name": "compare_across_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoen (the default) for English, es for Latin American Spanish.
questionYeswho_runs_it, recording, retakes or length.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real substance: each row carries its source page and the day it was read, and companies whose pages are silent are reported as 'not known' rather than omitted or guessed. That provenance and null-handling detail is exactly the behavior an agent needs to interpret results; only coverage/pagination limits are absent.

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?

Two sentences, front-loaded with the core purpose and followed by result-shape expectations. Some phrasing ('whose own pages say', repeated 'whether it is') is wordy, but no sentence is expendable.

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 two-parameter read tool with no output schema, the description covers purpose, the four query options, row contents (source page plus read date), and null handling — enough to call and interpret it correctly. Missing only operational detail such as how many companies are covered or result ordering.

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 100%, so baseline would be 3, but the description goes beyond the raw enum tokens by spelling out what each means in prose — 'who runs the interview (an AI or a person), whether it is recorded, whether it can be retaken, or how long it is.' The lang parameter is left entirely to the schema, which is acceptable given its self-explanatory enum values.

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 states a specific function: answer one question across every company, naming the four answerable questions (who_runs_it, recording, retakes, length). It implicitly contrasts with the single-company siblings by emphasizing 'for every company,' though it never names them explicitly.

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 the four enumerated question types and the 'every company' framing, which tells an agent this is the cross-company comparison path rather than a per-company lookup. There is no explicit when-not-to-use guidance or named alternative, so the routing decision is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources