neuron_schedule_recipe

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

No annotations are provided, so the description must carry the full behavioral burden. It conveys that a schedule is created or registered, but does not disclose whether an existing schedule for the same slug is updated, whether `enabled` defaults to true, what permissions are required, or what the operation returns. For a mutating tool, this is a significant transparency gap.

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?

The description is a single compact sentence with no filler, and it front-loads the main verb and object. It is efficiently written, though its brevity contributes to the missing behavioral and selection context penalized in other dimensions.

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 7 parameters, nested `variables`, two exclusive scheduling modes, no annotations, and no output schema, the overall package is only minimally adequate. The schema compensates for parameter details, but lifecycle semantics such as create-vs-update behavior, default `enabled` state, and what a successful response looks like are absent. The description is sufficient for a basic invocation but not fully complete for a mutation tool.

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?

The input schema already documents all seven parameters at 100% coverage, including mutual exclusivity between `interval_minutes` and `cron_hour`, so the baseline is 3. The description's 'interval or at a specific time' maps loosely to those fields but adds no new parameter-level meaning. The schema does the heavy lifting here.

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 names the specific action ('Schedule'), the resource ('recipe'), and the execution mode ('interval or at a specific time'), making the tool's purpose clear. It reads distinctly from immediate-run sibling `neuron_recipe_run`, though it does not explicitly name any sibling. Minor ambiguity remains about whether 'specific time' means cron-hour only or a one-off datetime.

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 phrase 'on an interval or at a specific time' implies this is for deferred or recurring execution, rather than immediate execution via `neuron_recipe_run`. However, the description does not state when not to use it, nor does it point to schedule-management siblings like `neuron_schedule_list`, `neuron_schedule_toggle`, or `neuron_schedule_remove`. The guidance is implied rather than explicit.

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