Create Hermes scheduled job

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false — describing a write operation without annotations contradiction. The description adds 'writing redacted receipts' which gives partial context about side effects. However, it does not explain persistence behavior, whether the created job persists across restarts, authentication/permission requirements, or how receipt redaction is significant. With some annotation coverage, a 3 is appropriate but the description could be richer.

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?

A single, compact sentence that front-loads the core action ('Typed POST /api/jobs wrapper that creates a scheduled Hermes cron job') and then enumerates the configurable fields. It's efficient with no filler. Slight deduction for cramming 'writing redacted receipts' at the end, which is behavioral context that might deserve more prominence, but overall very lean.

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?

With an output schema present, the description doesn't need to explain return values. The core create semantics, field list, and a side effect are covered. However, the description omits practical details that would help an agent invoke correctly: schedule format expectations, whether prompt/schedule have format restrictions, and the relationship to the run/pause/resume job lifecycle tools. It's adequate but not rich for a creation tool in a large tool family.

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 description coverage is 100%, so each of the 6 parameters already has a schema description (e.g., 'Optional model override', 'Prompt the cron job will run', 'Cron schedule expression or interval string'). The description groups them as 'skills, provider/model overrides, and delivery target' but adds no syntax, format, or interaction details beyond what the schema already documents. Baseline 3 is correct given full schema coverage.

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 says 'Typed POST /api/jobs wrapper that creates a scheduled Hermes cron job' — clear verb (creates) + resource (scheduled Hermes cron job). It lists the configuring fields (prompt, schedule, skills, provider/model overrides, delivery target) and the side effect (writing redacted receipts). It doesn't explicitly differentiate from the sibling jobs tools (list/get/update/delete/pause/resume/run), but 'creates' clearly implies a create operation distinct from the rest.

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?

The description states what the tool does and what fields it accepts, so an agent knows to use it when creating a new cron job. However, there is no explicit when-to-use guidance, no exclusions, and no mention of related alternatives (e.g., hermes_job_status, hermes_api_jobs_run) or constraints like whether schedule requires a specific cron format. Usage context is implied by the create semantics but not explicitly documented.

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