neuron_recipe_complete

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

With no annotations provided, the description carries the full disclosure burden and does reveal substantive behaviors: calling the tool automatically logs the outcome to recipe memory (a side effect), and the evolve-phase update is gated on memory-entry count. It does not disclose error states (e.g., no active run to complete) or whether completion is final/irreversible, which would round out the behavioral picture.

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?

Four short sentences with the core purpose front-loaded in the first sentence. Each subsequent sentence earns its place: auto-logging behavior, outcome structure guidance, and the conditional learnings rule. There is no filler, no repetition of schema content, and no ambiguity in ordering.

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 invocation contract is well covered: when to call, how to shape the outcome, and when to include learnings. Because there is no output schema, a brief note on return values would be useful, and error conditions (such as completing a run that has no active state) are undocumented — but these are minor gaps for a conceptually simple finalization tool whose prerequisites are clearly tied to neuron_recipe_run.

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, but the description adds meaning beyond the schema: it ties outcome structure to the recipe's Reflect section ('Provide the outcome data matching the recipe's Reflect section') and adds the conditional trigger for updated_learnings (5+ memory entries) that the schema's generic persistence note lacks. This gives an agent decision rules the schema alone does not.

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 uses a specific verb ('End') with a clear resource ('a recipe run started with neuron_recipe_run'), immediately positioning itself in the run lifecycle and distinguishing it from neuron_recipe_run (starts) and neuron_recipe_log (manual logging). The phrase 'Logs the outcome to the recipe's memory automatically' further differentiates it from the overlapping sibling neuron_recipe_log.

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 establishes clear usage context: it is the terminal partner to neuron_recipe_run ('End a recipe run started with neuron_recipe_run'), and it provides a conditional rule ('If the recipe has 5+ memory entries, also return the learnings'). However, it does not explicitly contrast with the overlapping alternative neuron_recipe_log or state when NOT to use this tool, so exclusion guidance is implicit rather than explicit.

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