Skip to main content
Glama

402cron

by com.402cron
OverviewDiscussionsAdmin

Create or update a scheduled task

create_task

Register a schedule against a destination you have already verified. Idempotent on "name": the same name updates the existing task instead of creating a second one. Creating costs nothing; each delivery ATTEMPT costs one credit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe https:// destination. It must already be registered and verified — see register_destination.
bodyNoThe body we send. Stored in the clear, so it must not carry credentials. A non-string is serialized as JSON.
cronYes5 fields, UTC only, one minute at the finest. Operators: * a-b a,b */n a-b/n. Names: SUN-SAT (day), JAN-DEC (month). Macros: @yearly @annually @monthly @weekly @daily @midnight @hourly. Day-of-week is 0-6 with 0 = Sunday; 7 also means Sunday. Write days as names (MON-FRI). Numbers differ between schedulers: Quartz, AWS EventBridge and Cloudflare number Sunday as 1, we and croniter as 0. Translated for you: "?". "?" as a whole day-of-month or day-of-week field becomes "*". A NUMERIC day-of-week next to "?" is refused, because "?" means the expression was written where Sunday is 1. Refused: Quartz L, Quartz W, Quartz #, six fields (seconds), seven fields (year), @reboot, @every, CRON_TZ= prefixes, time zones of any kind — each with a code saying what to send instead.
nameYesYour name for the task. Unique among your live tasks; creating with an existing name updates it.
methodNoHTTP method of the delivery. Default POST. GET and HEAD carry no body.
headersNoHeaders we send with the delivery. Stored ENCRYPTED at rest — put credentials here, never in the body.
timeoutMsNoHow long we wait for your server, 250-2000 ms. Answer 202 and do the work behind it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / cron / description
      Previous value: -"5 fields, UTC only, one minute at the finest. Operators: * a-b a,b */n a-b/n. Names: SUN-SAT (day), JAN-DEC (month). Macros: @yearly @annually @monthly @weekly @daily @midnight @hourly. Day-of-week is 0-6 with 0 = Sunday; 7 also means Sunday. Write days as names (MON-FRI). Numbers differ between schedulers: Quartz, AWS EventBridge and Cloudflare number Sunday as 1, we and croniter as 0. Refused: Quartz ?, Quartz L, Quartz W, Quartz #, six fields (seconds), seven fields (year), @reboot, @every, CRON_TZ= prefixes, time zones of any kind — each with a code saying what to send instead."New value: +"5 fields, UTC only, one minute at the finest. Operators: * a-b a,b */n a-b/n. Names: SUN-SAT (day), JAN-DEC (month). Macros: @yearly @annually @monthly @weekly @daily @midnight @hourly. Day-of-week is 0-6 with 0 = Sunday; 7 also means Sunday. Write days as names (MON-FRI). Numbers differ between schedulers: Quartz, AWS EventBridge and Cloudflare number Sunday as 1, we and croniter as 0. Translated for you: \"?\". \"?\" as a whole day-of-month or day-of-week field becomes \"*\". A NUMERIC day-of-week next to \"?\" is refused, because \"?\" means the expression was written where Sunday is 1. Refused: Quartz L, Quartz W, Quartz #, six fields (seconds), seven fields (year), @reboot, @every, CRON_TZ= prefixes, time zones of any kind — each with a code saying what to send instead."
  2. Changed1 schema field changed
    • changedInput schema / properties / cron / description
      Previous value: -"Five-field cron expression, UTC."New value: +"5 fields, UTC only, one minute at the finest. Operators: * a-b a,b */n a-b/n. Names: SUN-SAT (day), JAN-DEC (month). Macros: @yearly @annually @monthly @weekly @daily @midnight @hourly. Day-of-week is 0-6 with 0 = Sunday; 7 also means Sunday. Write days as names (MON-FRI). Numbers differ between schedulers: Quartz, AWS EventBridge and Cloudflare number Sunday as 1, we and croniter as 0. Refused: Quartz ?, Quartz L, Quartz W, Quartz #, six fields (seconds), seven fields (year), @reboot, @every, CRON_TZ= prefixes, time zones of any kind — each with a code saying what to send instead."
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and delivers real value: idempotency semantics (same name updates rather than duplicates) and a billing model (creation is free, each delivery attempt costs one credit). It does not disclose partial-update behavior (are unspecified fields cleared?), permission requirements, or what is returned, which keeps it short of 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tightly written sentences with zero filler. The action and its prerequisite are front-loaded, and the cost model is compressed into one clause with a deliberate capital on ATTEMPT.

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 7-parameter mutation tool with no annotations and no output schema, the description covers prerequisite, idempotency, and cost. Remaining gaps are the update-vs-create relationship with update_task and what happens to omitted fields on an update, so it is not fully complete.

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 description coverage is 100% and the schema itself is unusually rich (cron syntax, header encryption, body handling), so the baseline is 3. The description adds no parameter syntax or format detail beyond what the schema already states.

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 (register) and resource (a schedule against a verified destination) and clarifies it is an upsert via idempotency on name. It never addresses the update_task sibling, so an agent cannot tell from the description alone when create_task is preferred over update_task, keeping it below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides one prerequisite (destination must already be verified, pointing toward register_destination) and documents the idempotent-on-name behavior. However, with a dedicated update_task sibling, the description gives no explicit guidance on when to use this tool versus update_task, nor any exclusions.

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

All 402cron toolsInspect
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