Skip to main content
Glama
Sign In

Otto Intel

by services.ottoai
OverviewDiscussionsAdmin

Ask Otto

ask_otto
Read-onlyIdempotent

Ask Otto in plain words; Otto picks the right Otto service and answers, for one exact price. A failed answer costs nothing. Call it without x_payment to receive the quote: the chosen service’s price plus a $0.01 fee. Sign that requirement and call again with the same ask, the same price_cap_usd and the signed payload in x_payment. It answers about stocks and tokenized stocks by ticker, crypto prices by symbol, crypto news, X posts, prediction markets, DEX pools, web questions and domain lookups. An ask no Otto service fits is refused and nothing is charged. Market context only; not a recommendation. Hosted access: paid-only; each call costs the exact price its payment request quotes, at most $0.11 USDC, through x402, and preserves the free allowance.

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

Input Schema

NameRequiredDescriptionDefault
askYesThe question in plain words, for example "NVDA stock profile" or "how old is uniswap.org".
x_paymentNoSigned x402 payment payload. Omit it to receive the machine-actionable payment challenge, then retry with the signed payload.
price_cap_usdNoThe most this ask may cost in USD, fee included. Without it the limit is $0.11.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare a safe, idempotent, open-world read, so the description is free to focus on economics, and it does: x402 payment flow, a $0.01 fee, a hard cap of $0.11 USDC, no charge on failure or refusal, and idempotent retry with the same price_cap_usd. The remaining gap is that with no output schema it never describes the shape of a successful answer beyond the word '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?

Front-loads the core value proposition and then the payment mechanics in a logical order. It is dense and slightly run-on toward the end (the hosted-access sentence crams in paid-only status, per-call pricing, x402, and a 'free allowance' phrase whose meaning is unclear), but nearly every clause carries actionable information.

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 metered, open-world router with no output schema, the definition covers the pricing, refusal, and retry protocol that an agent most needs to avoid a bad call. The one omission that matters is the response format, since an agent must guess whether the answer arrives as text, JSON, or a service-specific payload.

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 the baseline is 3, but the description adds real meaning the schema cannot: x_payment's omission is the quoting mechanism, and price_cap_usd must be identical across the quote and the paid retry, with a $0.11 default. The example asks in the schema also clarify the expected granularity of 'ask'.

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 and resource: a plain-language ask is routed to the correct Otto service and answered for one exact price. It explicitly lists the domains it covers (stocks, crypto prices, news, X posts, prediction markets, DEX pools, web questions, domain lookups), which separates it from the dozens of single-purpose otto_* siblings.

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

Usage Guidelines4/5

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

Gives a concrete two-step invocation protocol: call without x_payment to get a quote, then retry with the same ask, same price_cap_usd, and the signed payload. It also states the refusal case (no matching service, nothing charged). What it does not say explicitly is when an agent should prefer a direct sibling such as otto_stock_token_quote over this router.

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

All Otto Intel toolsInspect
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