Skip to main content
Glama

List a workspace's schedules

list_schedules
Read-only

Show every schedule in a workspace with its cron, timezone, next run, and last outcome to check before creating new ones or debugging why a schedule appears broken.

Instructions

Shows every schedule on a workspace: what it fires, its cron and timezone, when it next runs, how the last run went, and why it is paused if it is. Check here before creating one — a second schedule on the same block is two jobs, not an edit.

READ canvasAheadOfPin FIRST when a schedule looks broken. A schedule runs the COMMITTED version it was pinned to, while deployed endpoints serve the live canvas — so one block can answer new code over HTTP while the cron beside it still runs the old one. When canvasAheadOfPin is true, canvasDrift lists exactly what differs; the symptom is reported as "the cron does nothing" about a cron that is firing perfectly. The fix is commit_workspace_version and then a schedule pinned to the new version — editing the block changes nothing on its own.

lastStatus is ONE outcome, not a history. Use list_schedule_runs before concluding anything about whether a schedule fires.

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": {
      "workspaceId": "<workspaceId>"
    },
    "name": "list_schedules"
  }
}

Input Schema

NameRequiredDescriptionDefault
workspaceIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.2/5.0
Behavior3/5

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

Annotations only declare readOnlyHint=true; the description adds genuinely useful semantics beyond that, explaining that schedules run the COMMITTED pinned version while endpoints serve live canvas, and that lastStatus is a single outcome rather than a history. However, much of that text is advisory about diagnosing failures rather than disclosing this tool's own behavior (no note on ordering, result size, or what a paused/null-last-run entry looks like), so it is useful context but not full behavioral disclosure of the call itself.

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 the concrete return fields, then diagnostic guidance, with emphasis markers guiding reading order. It is longer than a list tool usually needs, and the canvas-drift remediation paragraph (commit_workspace_version, re-pinning) drifts toward another tool's job, but the content is dense and non-repetitive.

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 single-parameter read with no output schema, the description covers what fields come back, the pinned-version semantics that make results surprising, and which sibling to consult for history. An agent has everything needed to call it and interpret the response correctly, including the "Shows every schedule" implication that no filtering/pagination is involved.

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 0% for the single workspaceId parameter, and the description only ties the call to "a workspace" without stating the ID format or how to obtain it via list_workspaces. It does establish scope (one workspace, no cross-workspace listing), which is some added meaning, but the parameter itself remains undocumented in both places.

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 ("Shows every schedule on a workspace") and enumerates exactly what is returned: what it fires, cron, timezone, next run, last run outcome, pause reason. It also distinguishes itself from create_schedule with "Check here before creating one — a second schedule on the same block is two jobs, not an edit," so an agent can tell it apart from siblings.

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 explicit routing rules: read canvasAheadOfPin first when a schedule looks broken, consult list_schedule_runs before concluding anything about firing, and check this list before creating a schedule. Conditions for using alternatives are named rather than left to inference.

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