Share by DeltaBreen

create_secret_handoff

Create a one-time page where a person types a secret (a password, a token, a short note). Their browser encrypts it and emails the link to notify_email; neither the service nor this connection ever sees the value. get_handoff_status confirms who it went to (emailed_to). For text only, not files.

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": {
      "notify_email": "<notify_email>"
    },
    "name": "create_secret_handoff"
  }
}

Input Schema

Name	Required	Description
`note`	No	Shown to the human on the page, e.g. "The staging database password".
`label`	No
`message`	No	The body of that email, in the human's words (up to 2000 characters).
`max_views`	No	How many times it may be read before it burns, 1 to 100; default 1.
`only_named`	No	Only notify_email can open it, after an emailed code. Recommended.
`expiry_days`	No	1 to 30 days; default 7.
`notify_email`	Yes	Who the secret is for. The page emails them the link the moment the human has typed the secret; required.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Adds substantive behavior beyond the annotations: the secret is end-to-end encrypted in the browser and never seen by the service or this connection, and the email fires the moment the human types the value. Annotations already declare non-read-only, non-destructive, closed-world, so the remaining gap is minor (no disclosure of what the caller receives back or failure modes).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences, each doing distinct work: purpose, mechanism, follow-up tool, and scope exclusion. Front-loaded with the core action and zero filler.

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 7-parameter creation tool with no output schema, the description covers the workflow, privacy model, and follow-up verification. The one real gap is that it never says what the calling agent gets back (a page URL? a page id?), which matters since the link goes to notify_email rather than to the caller.

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 coverage is 86%, so the schema already documents note, message, max_views, only_named, expiry_days and notify_email. The description reinforces notify_email's timing semantics ('emails them the link the moment the human has typed the secret') but adds nothing about max_views, expiry_days, or only_named beyond what the schema states — baseline 3 applies.

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 — create a one-time page where a person types a secret — plus the mechanism (browser-side encryption, emailed link to notify_email). It is clearly distinguishable from create_upload_handoff (files) and create_request_page, which an agent can tell apart without opening any schema.

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?

Explicitly scopes to text only, not files, which routes the agent away from create_upload_handoff, and names get_handoff_status as the confirmation follow-up. It stops short of stating when to prefer this over create_request_page or other sibling flows, so no full when-not matrix.

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

All Share by DeltaBreen 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?