neuron_recipe_run

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

With no annotations, the description carries the burden of explaining side effects. It discloses that rules are injected as 'non-negotiable constraints that override recipe strategy' and that variables are auto-filled from profile, which reveals precedence and stateful behavior. It doesn't mention the return value or broader side effects, but the key behavioral traits are covered.

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?

Three sentences with no redundancy: the first states the action, the second enumerates what gets loaded, and the third explains rule precedence and the follow-up call. Every sentence earns its place and the core behavior is front-loaded.

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 description is informative about inputs and execution behavior, but there is no output schema and the description fails to state what the tool returns (e.g., a run ID or status). Since the agent is told to call neuron_recipe_complete afterward, knowing what identifying information is returned is essential for correct invocation. This missing detail is a clear gap.

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 the baseline is 3. The description adds meaning beyond the schema by explaining that variables are interpolated into agent.md, auto-filled from profile, and that rules override recipe strategy. This enriches the schema's dry 'merged on top' phrasing with execution context.

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 specific verb and resource, 'Start a recipe run', immediately identifying the tool's function. It then details what the run loads (agent.md, learnings, resolved variables, active rules), clearly distinguishing it from sibling recipe tools like neuron_recipe_list or neuron_recipe_complete.

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 provides clear context for when to use this tool: to initiate a recipe run, and it explicitly instructs to call neuron_recipe_complete when done. However, it does not explicitly state when not to use it or name alternatives for other operations (e.g., inspecting recipes), leaving the differentiation mostly implicit.

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