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

With no annotations, the description carries the full burden and does so unusually well: each run costs delivery attempts, failures trigger a signed alert to alert_url (and again on recovery), runs that cannot start never report but flip the cron to failing, calling with the same name replaces the existing cron, and there is a hard cap of 10 crons. These are non-obvious operational consequences an agent could not get from the schema.

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?

Purpose is front-loaded in the first sentence and every subsequent block addresses a distinct concern (cost, dead man's switch, reporting, replacement, quota). It is dense with stacked parentheticals and cross-references to set_wake and schedule_http, which slows parsing, but little of it is fillers.

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?

For an 11-parameter tool with nested header objects, no annotations and no output schema, the description covers cost, failure, quotas and update semantics thoroughly. The notable remaining gap is the return value: nothing says what create_cron hands back (a cron object, an id, or just confirmation), which matters when there is no output schema.

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 91%, so the schema already explains most parameters. The description still adds real meaning: the schedule must have a single minute value (at most hourly) with a worked example, name reuse means replacement rather than an error, and report/alert_url/callback_url are tied together into a coherent reporting story.

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?

Opens with a specific verb+resource and scope: 'Run an HTTP request on a recurring schedule', then pins the schedule format to a 5-field UTC cron with a single minute value. It distinguishes itself from the one-off sibling by referencing schedule_http only for shared semantics ('as schedule_http's capture', 'Same rules as schedule_http'), so an agent can tell this is the recurring variant.

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?

Gives clear conditional guidance: use report: "failures" for a quiet healthy cron, set alert_url (or "inbox") to catch crons that cannot start, and pass callback_url+capture to see run results. It stops short of an explicit 'use schedule_http for a single request instead' routing statement, so the when-not is only inferable from the recurring framing.

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