Inbox Triage

Inbox zero: start the daily pass

inbox_zero_start

Starts the daily pass. Takes the triage lease and returns the next 10 messages that need the person, numbered, VIPs first, then people, then the rest, each with a suggested action and why, and a batchId. Show every row on its own numbered line, never grouped, ask, then call inbox_zero_decide with that batchId. The daily pass covers mail since the inbox was connected; catchUp:true works the backlog instead, mail that was there when you connected, and the two sessions exclude each other. ask:true asks the person in their app to apply all suggestions, answer in chat, or skip the batch; askedInApp tells you whether they answered. When the client cannot ask, the result carries a decideUrl: give the person that link, and call inbox_zero_decide as usual if they answer in chat instead. inbox_zero_wait holds until they have decided on that page. Work on your own only on a clear instruction or a saved agentRules rule; otherwise suggest and wait. Prefer archive over trash; report counts and undo ids.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "inbox_zero_start"
  }
}

Input Schema

Name	Required	Description
`ask`	No	Ask the person in their app about the returned batch (hosts with form prompts only). Default false.
`inbox`	No	Inbox name or id; leave empty for all inboxes
`catchUp`	No	Work through the mail from before the inbox was connected, which the daily pass leaves out. Default false.
`agentLabel`	No	The label you already hold the triage lease under, if any. Default inbox_zero.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond annotations: discloses that it takes a triage lease, that start sessions are mutually exclusive, that ask:true can prompt the person in-app with askedInApp feedback, and provides a decideUrl fallback with inbox_zero_wait holding until decision. This is rich operational context not encoded in the schema or annotations. No contradiction with readOnlyHint=false (taking a lease is a state write).

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?

Purpose and core behavior are front-loaded in the opening sentences, and nearly every clause carries operational value. It is dense with long compound sentences, but little is filler given the tool's complexity.

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

Completeness5/5

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

No output schema exists, yet the description specifies the return contents (numbered rows, VIP/people/rest ordering, suggested action and why, batchId, askedInApp, decideUrl). Combined with the workflow handoff to inbox_zero_decide and inbox_zero_wait, an agent has everything needed to call it correctly.

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 schema already documents all four params; baseline is 3. The description adds meaning beyond it: catchUp works mail from before connection and excludes the daily pass, ask prompts the person and reports askedInApp, and agentLabel is the lease label. This modestly exceeds the schema's own wording.

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+resource ('Starts the daily pass. Takes the triage lease') and describes the return shape (next 10 messages needing the person, VIPs first, with batchId). It clearly distinguishes itself from siblings inbox_zero_decide, inbox_zero_wait, and inbox_zero_stop by naming them and their roles in the flow.

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?

Explicitly routes the agent: catchUp:true for backlog vs the daily pass, the two sessions exclude each other, call inbox_zero_decide with the batchId after asking. It also gives a decision rule ('work on your own only on a clear instruction or a saved agentRules rule; otherwise suggest and wait') and a fallback path (decideUrl when the client cannot ask).

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

All Inbox Triage 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?