Skip to main content
Glama

Ask WebKnox

ask_webknox
Read-only

Shows the user an interactive WebKnox answer card, with its sources, for questions that have one: comparisons of two to four things with photos ("ravens vs crows"), weather forecasts for a named place, sunrise, sunset and moon phases, nutrition facts of a food, recipes, translations and word definitions, unit conversions and calculations, the time in a city and countdowns, pictures of a subject, videos, music, radio stations, podcasts and sounds, jokes, quotes, fun facts and what happened on this day, and who a named person is or what a named place or chemical element is, with a photo, a map or its place in the periodic table. It has no cards for explanations, advice, opinions, coding or writing. For a question without a card, the result says so and shows nothing.

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": "ask_webknox"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitsNoUnits for weather and conversions, when the user prefers one system.
localeNoThe user's language, for the card's labels: en, de, fr, es, pt or it.
questionYesThe question as one self-contained sentence in the user's language that names the place, food or things it is about; a follow-up such as "and tomorrow?" written out as a full question.
timezoneNoThe user's IANA time zone, such as Europe/Berlin, when known.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / question / description
      Previous value: -"The question as one self-contained sentence in the user's language, naming the place, food or things it is about. Rewrite follow-ups such as \"and tomorrow?\" into a full question."New value: +"The question as one self-contained sentence in the user's language that names the place, food or things it is about; a follow-up such as \"and tomorrow?\" written out as a full question."
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false and idempotentHint=false. The description adds genuinely new behavior: the tool renders a visible UI card to the user, the card includes sources, and an unsupported question yields a result that explicitly says so and shows nothing. It omits latency, rate limits, or reliability characteristics of the open-world lookup.

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 key sentence is front-loaded, which is good, but the middle is a sprawling run-on enumeration of dozens of card types that could be compressed into a few categories. The exclusion and fallback sentences are well placed at the end, so structure is sound even though length is excessive.

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 returns, and it does explain that a card is shown with sources and that an empty result states the absence. For a single-required-parameter lookup tool with full schema coverage and rich annotations, this is nearly complete, missing only expectations about response speed or failure modes.

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 question, units, locale and timezone are already fully documented with formats and enums. The description adds only indirect hints, e.g. that questions name a place, food or subject, which is consistent with but not richer than the schema. Baseline 3 applies.

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 opening sentence names a specific verb and artifact: shows an interactive WebKnox answer card with sources. The long enumeration of card categories further pins down scope, though the list format blurs the core purpose somewhat. There are no siblings, so differentiation is not a factor.

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

Usage Guidelines5/5

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

It states positively when a card exists (comparisons, weather, nutrition, recipes, translations, conversions, media, jokes/quotes, named entities) and explicitly when it does not: explanations, advice, opinions, coding or writing. It also describes the fallback behavior for unsupported questions, leaving nothing to infer.

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