Skip to main content
Glama

create_schedule

Schedule a browser task to run automatically at a fixed interval of at least one hour, so recurring web checks or actions run without manual input.

Instructions

Schedule a browser task to run automatically on a fixed interval (min 1 hour). Each run is a normal billed task. LLM key: same rules as run_task (the workspace's default saved key unless llm_key_id is given); the schedule stores only the saved key's id. With no llm and no saved key, the schedule runs on Browsa's hosted model and the result says so. Pass llm "browsa", "browsa-fast" or "browsa-smart" to choose a hosted tier.

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": {
      "task": "<task>",
      "interval_seconds": "<interval_seconds>"
    },
    "name": "create_schedule"
  }
}

Input Schema

NameRequiredDescriptionDefault
llmNoLLM id. Omit to use the workspace's default saved key (hosted model if none is saved). Hosted tiers: "browsa", "browsa-fast", "browsa-smart".
nameNoOptional label for the schedule.
taskYesPlain-English task instructions (same as run_task).
countryNo2-letter egress country.
max_stepsNoMax agent steps per run.
reasoningNoHow much the model reasons. Omit for the tier's or the provider's default.
llm_key_idNoId of a saved LLM key (see list_llm_keys). Optional.
initial_urlNoOptional pre-navigation URL.
llm_api_keyNoPer-schedule LLM key. Rarely needed: prefer a saved key. Overrides llm_key_id.
interval_secondsYesRun interval in seconds. 3600 (1h) – 2592000 (30d).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does substantial work: billing per run, the 1-hour floor, the fact that only the saved key's id is stored, and the hosted-model fallback whose result is self-declaring. It omits failure behavior, whether a schedule can be paused or edited, and permission requirements, which keeps it from a 5.

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?

It is front-loaded with the core purpose, and each following sentence covers a distinct concern (billing, key resolution, hosted fallback). The hosted tier list appears in both the description and the schema, a small duplication, but nothing is wasted overall.

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 10-parameter creation tool with no annotations and no output schema, the description covers the highest-risk ambiguities: cost per run and which credential will actually be used. It never hints at what is returned (a schedule id), which an agent would need to later reference the schedule.

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, but the description adds resolution order not obvious from the schema: llm is overridden by llm_key_id, which is in turn overridden by llm_api_key, and a missing key silently falls back to a hosted tier. The hosted tier names are repeated from the schema, which is minor redundancy.

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?

The opening sentence gives a specific verb (schedule), resource (a browser task), and scope constraint (fixed interval, min 1 hour). It is immediately distinguishable from run_task, which it references as the one-off analogue, and from list_schedules.

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?

It establishes the recurring-use context and warns that every run is a normal billed task, which is real when-to-use guidance. It does not explicitly route an agent to run_task for a one-off or to list_schedules for inspection, so it stops short of naming alternatives and exclusions.

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