Stratum Shifts

Publish week

publish_week

Destructive

Use this when the user is ready to share a week with staff, or to share changes made since it was published, or to call a published week off (publish it with no shifts). Makes a read-only link anyone with it can open; staff see the version last published, so publish again after edits. On the Team plan email_staff emails each scheduled person their shifts the first time, and afterwards only the people whose shifts changed, with just their changes. Needs the user to be signed in. Staff are emailed only when email_staff is true.

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": {
      "week_start": "<week_start>"
    },
    "name": "publish_week"
  }
}

Input Schema

Name	Required	Description
`week_start`	Yes	The week to publish: "this", "next" or "last" (counted from today in the workplace's time zone), or any date in that week as YYYY-MM-DD. For next week pass "next".
`email_staff`	No	Email each scheduled person who has an email address. Team plan only.
`workplace_id`	No	Workplace id. Omit to use the first workplace.

Output Schema

Name	Required	Description
`fill`	No
`week`	Yes
`labor`	Yes
`links`	Yes
`staff`	Yes
`checks`	Yes
`notice`	Yes
`shifts`	Yes
`totals`	Yes
`account`	Yes
`coverage`	Yes
`requests`	No	Time-off requests from staff waiting for an answer
`workplace`	Yes
`schemaVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Adds substantial behavior beyond annotations: a read-only link accessible by anyone holding it (matching openWorldHint), staff seeing only the last published version so edits require re-publishing, the unusual off-switch semantics of publishing with no shifts, an auth prerequisite, and first-publish vs. changed-shifts-only email dedup. None of this is inferable from the schema or hints.

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 a usage trigger and dense with actionable detail; nearly every clause carries new information. The closing sentence 'Staff are emailed only when email_staff is true' restates what the preceding two sentences already established, a minor redundancy.

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?

For a publish operation with destructive semantics, the description covers the auth requirement, the visibility model, the re-publish workflow, the unpublish path, and the email side effect. With an output schema present, return values need not be explained, so nothing material is missing.

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% and already explains week_start formats and Team-plan scoping for email_staff. The description still adds real meaning: the first-time-vs-subsequent email behavior and the fact that emails go only to people whose shifts changed. It does not mention workplace_id, but that is already fully covered by the schema.

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 (publish) and resource (a week) and immediately frames the outcome: a read-only link anyone with it can open. It is unmistakably distinct from siblings like show_week, copy_week and edit_shifts, which do not create a shared public version.

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 three explicit triggers (ready to share, share changes since last publish, call a week off by publishing with no shifts) and an explicit re-use rule ('publish again after edits'). This is exactly the when-to-use guidance an agent needs with no inference required.

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

All Stratum Shifts 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?