Conecto

Ask a person to approve

notify_request_approval

Ask a person before you act: approve or decline (or pick one of up to 5 options), with an optional comment, on a one-time page sent through a saved channel or by email. The first answer reaches you as the event notify.answered (subscribe a webhook, or check notify_get_approval). For refunds, big orders, offers and posts. Anyone holding the link can answer, so send it only to the person who decides. Email follows the account's rules (new addresses are capped a day). $0.01 a request, $0.02 more by email; the answer is free. Costs $0.01 a request, $0.02 more by email (at most $0.03 a call); nothing if it fails.

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": "notify_request_approval"
  }
}

Input Schema

Name	Required	Description
`email`	No	Or an email address to send it to.
`channel`	No	A saved channel to send it to (notify_list_channels).
`comment`	No	Offer a comment box.
`details`	No	What the person should know first.
`options`	No	The answers to pick from. Default: Approve, Decline.
`question`	Yes	What to decide, e.g. "Refund order 1042 in full ($849)?"
`reference`	No	Your own reference, sent back with the answer (an order number, a refund).
`expires_in_hours`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: anyone holding the link can answer, email follows account rules with a daily cap for new addresses, first answer wins via event or polling, and per-request/per-email pricing with a fail-for-free guarantee. This is exactly the operational context an agent needs for an openWorld, non-idempotent call.

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?

Front-loaded and mostly tight, but the pricing sentence is stated twice almost verbatim ('$0.01 a request, $0.02 more by email' then 'Costs $0.01 a request, $0.02 more by email'), wasting a sentence in an otherwise short description.

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 and 8 parameters, the description covers what gets sent, who can answer, how the answer returns, cost, and failure behavior. The only meaningful omissions are the expiry window and how the reference value round-trips, both handled by the schema.

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?

With 88% schema coverage the baseline is 3, but the description adds that a channel or an email is used to deliver the page (mutually exclusive choice not stated in the schema), the option count ceiling, and the optional comment. It doesn't clarify expires_in_hours or reference, which remain schema-only.

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 actor, verb, and resource: ask a person to answer a one-time approval page. It clearly distinguishes itself from notify_send (one-way push) and notify_get_approval (the retrieval side) by naming the answer delivery path.

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 concrete use cases (refunds, big orders, offers, posts) and the caution about sending links only to the decider. It names notify.answered and notify_get_approval as the retrieval route, though it never explicitly contrasts itself with the plain notify_send tool.

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

All Conecto tools Inspect

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

Need Help?