Skip to main content
Glama

ask

Delegate one-shot prompts to free web LLMs for summarizing, translating, small code snippets, second opinions, or web lookups. Returns the reply text from a fresh chat each call.

Instructions

One-shot question to a free web LLM (new chat each call). Good for summarize/translate/ small code/second opinion/web lookup. Returns the reply text.

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": {
      "prompt": "<prompt>"
    },
    "name": "ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYes
timeoutNo
providerNogemini

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose meaningful traits: one-shot semantics, a fresh chat per call, that the backend is a free web LLM, and that the raw reply text is returned. It omits operational behavior an agent would want — rate limits, what happens on timeout (default 120s), error/refusal behavior, and any privacy implication of sending the prompt to an external free LLM.

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 compact, front-loaded sentences with no filler; the core operation and the key statefulness caveat appear first. The task-example list is dense but each item earns its place by widening the recognizable use cases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is rightly omitted, and the one-shot framing is complete. Still, for a tool with three undocumented parameters and an outsourced third-party dependency, the definition leaves genuine gaps around provider selection, timeout semantics, and failure modes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate and it does not: prompt, timeout, and provider are never mentioned, and their names alone leave ambiguity (is timeout in seconds? what providers exist and how does 'provider' change behavior?). Only an implicit mapping exists — the "question" is the prompt and "returns the reply text" hints at the result.

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?

States a specific verb and resource — a one-shot question to a free web LLM — and adds concrete task examples (summarize, translate, small code, second opinion, web lookup) that tell an agent what class of work this fits. It does not name or differentiate from the sibling tools, but the purpose is specific enough that confusion with generate_image or login is unlikely.

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?

The "Good for ..." clause implies when to use the tool, and "new chat each call" warns that no conversation state persists. However, there are no explicit exclusions, no guidance on when another tool (e.g., the image generator or provider listing) is preferable, and no advice on when a second call is warranted versus chaining context manually.

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

Deploy Server

Other Tools