next_runsCompute the next N run times (UTC ISO-8601) for a cron expression. Optionally start from a given time.
| Name | Required | Description | Default |
|---|---|---|---|
| from | No | Optional ISO-8601 start time (default: now). | |
| count | No | How many upcoming runs to return (1-50, default 5). | |
| expression | Yes | A cron expression or @alias. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds the output timezone (UTC ISO-8601) and optional start time, which provides some value beyond annotations, but does not disclose error handling or edge cases like invalid cron expressions. This meets the baseline for a safe read-only tool.
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?
Two concise sentences, with the primary purpose front-loaded. Every word adds value; no fluff or repetition of schema/annotation details.
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?
The tool is simple and the description fully captures its behavior: computing N future run times with an optional start. Schema covers parameter constraints, and annotations cover safety. No output schema is needed because the tool's return type is self-evident from the description.
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?
Input schema has 100% coverage with clear descriptions for all three parameters. The description reinforces that the start time is optional, but adds limited new meaning beyond schema details. Baseline of 3 is appropriate since schema handles the heavy lifting.
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?
Description clearly states it computes next run times for a cron expression, using specific verb ('Compute') and output format (UTC ISO-8601). This distinguishes it from sibling tools like describe_cron, which likely explains cron syntax rather than calculating future run times.
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?
No guidance on when to use this tool versus alternatives such as describe_cron. The description only mentions an optional start time parameter, but does not explain use cases or exclusions, leaving the agent without clear selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools have overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all answer factual questions with subtle differences that are not immediately clear. Additionally, five polymarket tools cover similar ground (arbitrage, edges, fill risk, spread), making it hard to pick the right one without reading the full descriptions.
Tool names are consistently snake_case and mostly follow a verb_noun pattern (e.g., describe_cron, next_runs, validate_claim). Minor deviations exist (bet_research, entity_profile, pipeworx_trending) but the overall style is predictable and readable.
33 tools is well over the high end for a focused server, and the server name 'Crontab' implies a narrow cron utility while most tools are a broad data-research platform. This mismatch makes the count feel bloated and poorly scoped.
For a cron server, the set is severely incomplete: only describe_cron and next_runs exist, with no create/delete/update functionality. For the actual data-research domain, it is rich but lacks clear CRUD coverage for many resources, and the inclusion of unrelated cron/memory tools creates dead ends.