Cron runs across timezones
Scored across 1 tool
With a single tool there is no cross-tool ambiguity to resolve, so misselection risk is essentially zero. The only caveat is that one tool bundles three modes (expression explanation, next-run projection, DST inspection) whose selection depends on argument shape rather than distinct tool names.
The lone name, explore_cron, follows a clean verb_noun snake_case convention that matches the broader MCP ecosystem norm. There is no competing convention to create inconsistency.
One tool is thin for a server, though the domain (cron expression analysis) is narrow enough that a single entry point is defensible and the description is dense with capability. Splitting explain vs. next-runs vs. DST could have improved clarity, but the count is not a serious mismatch.
The surface covers the core domain well: explaining a five-field expression, projecting up to 20 future runs in a named timezone, and surfacing DST transitions, with search bounded at 1,830 days. Gaps are acknowledged and reasonable (no execution, no macros/seconds/L/W/#), though there is no dedicated validation-only path for malformed expressions.
Use this when you want to explain a five-field cron expression, find its next runs in an IANA timezone, or inspect daylight-saving transitions. Supports numeric *, lists, ascending ranges, and steps. Requires an explicit timestamp reference. Searches up to 1,830 days and returns up to 20 runs strictly after it. Does not execute jobs or support names, macros, seconds, years, ?, L, W, or #.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of next occurrences, e.g. 5. Defaults to 5; maximum 20. | |
| timezone | Yes | Explicit IANA timezone, e.g. America/New_York, Europe/Warsaw, or UTC. | |
| reference | Yes | Explicit reference timestamp with seconds and Z or UTC offset, e.g. 2026-01-01T00:00:00Z. Runs are strictly after it. | |
| expression | Yes | Five-field numeric cron expression, e.g. 0 9 * * 1-5. Fields: minute hour day-of-month month day-of-week; Sunday is 0 or 7. |
| Name | Required | Description |
|---|---|---|
| found | Yes | |
| fields | Yes | |
| request | Yes | |
| complete | Yes | |
| day_rule | Yes | |
| timezone | Yes | |
| warnings | Yes | |
| downloads | Yes | |
| reference | Yes | |
| requested | Yes | |
| dst_policy | Yes | |
| expression | Yes | |
| search_end | Yes | |
| occurrences | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only and non-destructive semantics, so the description wisely spends its words on other traits: the mandatory explicit reference timestamp, a 1,830-day search horizon, and a 20-run cap strictly after the reference. It does not discuss timezone database versioning or ordering guarantees, but the operational boundaries are disclosed well beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each carrying distinct information: purpose, supported syntax, execution constraints, and exclusions. The capability statement is front-loaded and nothing is padded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given an output schema exists, the description needn't explain return values; it instead covers the inputs' constraints, search bound, and unsupported syntax. An agent has everything needed to call this correctly and to recognize invalid inputs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so a baseline of 3 applies. The description earns above baseline by documenting the supported cron subset (numeric *, lists, ascending ranges, steps) and reiterating 'strictly after' reference semantics and the 20-run ceiling — grammar details the schema does not supply.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a concrete verb and resource ('explain a five-field cron expression') and enumerates the three capabilities: explanation, next runs in an IANA timezone, and DST transition inspection. It also states what the tool is not ('Does not execute jobs'), which removes the most plausible misreading.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Use this when you want to ...' gives an explicit trigger condition, and the closing sentence lists unsupported inputs (names, macros, seconds, years, ?, L, W, #) so the agent knows when to look elsewhere. There are no sibling tools, but the exclusions cover the main failure modes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
explore_cronFind meeting times across TZs
Time zone conversion, meeting-slot finding across countries, DST checks and .ics invites. All.
Validates cron expressions and finds DST bugs that make jobs silently skip or double-fire.
Cron expression parser: explains any cron + returns next N fire times. Timezone-aware.
Add one secure layer between your agents and this server.