Skip to main content
Glama

askround_ask

Ask one question to several AI assistants with web search and get a brief of which products they recommend, how each ranks per provider, and the claims and rivals behind every fact.

Instructions

Ask one question to several AI assistants (OpenAI, Gemini, Anthropic, Perplexity) with web search, each several times, and read what they recommend. Returns a brief of a few hundred tokens: for each product the runs naming it and its best position per provider, its top claims and the rivals, each fact with the ids of the answers it came from ('openai#2'). Read an answer, or the passage behind a fact, with askround_answer; detail: true returns the full report instead. Refused before any call if the question names a product it tests, carries personal data, or is estimated above max_cost.

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": "askround_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
runsNoruns per provider (default 3)
freshNoask again even if the same round was asked within the day; by default a recent one is returned at no cost
detailNothe full report, not the brief
searchNoweb search (default true)
extractNoread recommendations and claims with a model (one call per answer)
localesNoe.g. ['BR:pt-BR']
max_costNorefuse, before any call, a run estimated above this (USD)
productsNoproducts to report on, each 'Name,alias,domain'
questionYesthe question, as a person would ask it
providersNoonly these providers (default: every one with a key)
backgroundNostart it as a job and return at once (a round takes minutes); read it with askround_job

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses latency ('a round takes minutes'), the cost model (max_cost refusal before any call, cached recent rounds at no cost), the asynchrony option, and the exact refusal rules. It also explains provenance encoding ('openai#2') so the agent knows how facts link back to answers.

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?

The core purpose and output format are front-loaded in the first sentence, and every subsequent clause carries information (output shape, sibling routing, refusal conditions). The second and third sentences are long and comma-dense, which costs some readability, but there is no filler.

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?

No output schema exists, so the description must describe returns — and it does concretely: per-product run counts, best position per provider, top claims, rivals, and fact-to-answer id linkage, plus the token-size expectation. Combined with the latency, cost and refusal disclosures, an agent has everything needed to call this correctly for a complex eleven-parameter, multi-provider tool.

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 all eleven parameters are already documented; the baseline of 3 applies. The description adds only marginal meaning beyond the schema — clarifying that detail: true yields the full report rather than the brief, and that max_cost causes refusal before any call — while runs, fresh, extract, locales, products and providers are left to the schema.

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 opens with a specific verb and resource — ask one question to several named AI assistants with web search, several runs each — and states the output shape (a brief of a few hundred tokens per product). It is unmistakably distinct from askround_answer (single answer/passage), askround_job (background read) and the report/diff siblings.

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 routes the agent explicitly: use askround_answer to read an individual answer or the passage behind a fact, use detail: true for the full report instead, and use background with askround_job for a job that takes minutes. It also names three negative conditions (question names a product under test, carries personal data, or exceeds max_cost) that cause a pre-call refusal.

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