Skip to main content
Glama

scheduleDashboardRefresh

Schedules, changes or stops automatic dashboard data refreshes with a cron expression, even when no assistant is running. Cron runs replace page data at set times and clear outdated coach notes.

Instructions

Turns on, changes or stops the automatic refresh of a dashboard page. Use it only when the user asks for it or says yes to the question of a dashboard prompt. A job in the scheduler of the computer (launchd, cron or Task Scheduler) replaces the data of the page at the given times, also with no assistant open. The refresh removes the coach notes, because old notes do not agree with new data. The computer must be on at that time. The page must exist (writeDashboard first). last is the last automatic run: its time, the pages that it could not update, with the error, and in partial the pages that it updated with gaps. A page shows a note when its update is more than 1 hour late: last tells why. cron: convert what the user says, in any language, into a 5-field cron expression in local time: minute hour day-of-month month weekday, numbers only (0 = Sunday), e.g. "0 7 * * 1-5" for weekdays at 7. Two runs must be at least 1 hour apart. The cron is for all scheduled pages; path adds that page (default the main page); off stops the refresh of path, or of every page when no path is given. Without arguments it only reads. The reply has next, the next runs in local time: tell them to the user in their language, so they can check the schedule.

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": "scheduleDashboardRefresh"
  }
}

Input Schema

NameRequiredDescriptionDefault
offNoStop the refresh
cronNominute hour day-of-month month weekday, e.g. "0 7 * * *"; default 0 7 * * *
pathNoThe .html file; relative paths are inside the data dir

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.13.0

TDQS

A3.9/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden and does well: it discloses the destructive side effect (refresh removes coach notes), the environmental requirement (computer must be on at that time), the 1-hour minimum spacing between runs, and that the job runs without the assistant open. The return payload (last, next, partial) is also explained. Missing: permission/auth needs and whether enabling replaces a prior schedule.

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?

Content is valuable but the structure is a dense block of run-on fragments (cron format, off behavior, last/next semantics) with inconsistent ordering. Key routing guidance, the 'off with no path stops everything' rule, is buried mid-paragraph, so an agent may miss it on a skim.

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 3-param mutation tool with no annotations and no output schema, the description covers prerequisites, side effects, scheduling semantics, error reporting via last, and the reply fields. Only auth/permission behavior and the exact shape of the returned object remain unstated.

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 already 100%, so baseline is 3, but the description adds real meaning: it explains cron conversion from natural language, the 5-field local-time format with 0=Sunday, the 1-hour spacing rule, that cron applies to all scheduled pages while path scopes to one page, and that off with no path stops every page. This is semantics the schema does not carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb set and resource: turns on, changes, or stops automatic refresh of a dashboard page, and names the scheduling mechanism (launchd, cron, Task Scheduler). It is clearly distinct from read siblings like getDashboardData and from writeDashboard/editDashboard, though it never explicitly names those siblings.

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 an explicit gating condition: use only when the user asks for it or answers yes to the dashboard prompt, and states the prerequisite that the page must exist (writeDashboard first). It also clarifies that no arguments means read-only. It stops short of contrasting with editDashboard for adjacent needs.

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