RelayLink

Save a hand-off to yourself

save_handoff

Save where the user has got to, into their own RelayLink inbox, so another assistant on the same account can pick it up — worked through here, resumed in ChatGPT tonight. One call and no approval round: it is addressed to the user's own account, reaches nobody else and sends no email, so there is no third party to put words in front of. Write it for a reader with zero context, because that is exactly what the next assistant is. It is recorded as composed by you and is never labelled as the user's own words. resume_handoff is what picks it up. Offer it when the user says they are stopping, switching assistants, or asks to save where they got to.

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": {
      "goal": "<goal>",
      "progress": "<progress>",
      "nextStep": "<nextStep>"
    },
    "name": "save_handoff"
  }
}

Input Schema

Name	Required	Description
`goal`	Yes	What the user is trying to achieve, one sentence. The first thing the next assistant reads.
`topic`	No	Short topic, a few words. Required for a new hand-off; omit it when adding to one with threadId.
`nextStep`	Yes	The one concrete thing to do next, as an instruction to the assistant that picks this up.
`progress`	Yes	150–400 words for a reader with zero context: what has been done, what was tried and dropped, what is known now. Compress — this is a briefing, not a transcript.
`threadId`	No	An existing hand-off thread_id, to add to work already in progress.
`decisions`	No	Decisions already made, with confidence and reversibility, so the next assistant does not reopen them.
`openQuestions`	No	What is still undecided or unknown.
`attachmentVersionIds`	No	The user's own Ready documents to carry with this hand-off, by version_id (from attachment_create_text, attachment_list, or attachment_upload_link) — at most 5, 5,242,880 bytes together. No approval round for these either: a hand-off reaches nobody but the user's own account.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Goes well beyond the annotations: no approval round, reaches nobody but the user's own account, sends no email, and is recorded as composed by the assistant rather than the user's own words — all real disclosure an agent could not infer from readOnlyHint=false / destructiveHint=false / openWorldHint=false. Minor gap: the tool is non-idempotent per annotations, and the description never says that each call creates a new hand-off rather than updating one (threadId semantics only appear in the schema).

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-loaded with what the tool does and its privacy scope, then when to offer it, then the sibling pointer. Dense and purposeful, though the privacy rationale and the authorship clause could be tightened without losing meaning.

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?

There is no output schema, and the description never says what a call returns — notably the thread_id needed later by resume_handoff and threadId, which an agent needs to chain the two calls. Otherwise complete: destination, privacy scope, approval behavior, and writing standard are all covered.

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; the description earns a bump by giving authoring guidance that directly shapes the required goal/progress/nextStep content ('write it for a reader with zero context, because that is exactly what the next assistant is'). It does not restate field-level detail already in the schema, which is correct.

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 destination: saving the user's current position into their own RelayLink inbox for another assistant on the same account. It explicitly names the counterpart tool (resume_handoff is what picks it up), so the agent can separate the save side from the resume side without reading either schema.

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?

Gives a concrete trigger set ('when the user says they are stopping, switching assistants, or asks to save where they got to') and names the sibling that consumes the output. Both the when and the pairing are spelled out rather than implied.

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

All RelayLink 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?