reinvent_reinforcement_learning

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

With no annotations, the description carries the full burden. It discloses key behaviors: dry_run previews config without writing/launching, skip_validation=False validates SMILES/TOML, launch controls whether the agent runs the job, and it details required stage/component structure. It doesn't cover all side effects (e.g., file creation, error handling) but provides substantial transparency.

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 front-loaded with a clear purpose, then lists behaviors and config requirements. Every sentence adds value, though the nested bullet lists make it dense. Appropriate for the complexity, with no wasted words.

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?

This is a complex tool with 21 parameters, no output schema, and no annotations. The description thoroughly covers the stages structure and gives usage context, but it omits explanations for many parameters and doesn't describe return values or failure modes. It's adequate but has clear gaps for fully independent use.

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 0%, so the description must compensate. It thoroughly explains the central 'stages' parameter and clarifies dry_run, skip_validation, and launch, but it leaves many other parameters (e.g., distance_threshold, diversity_filter, inception, sample_strategy) unexplained. This is only partial compensation for a 21-parameter tool.

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 'Run staged reinforcement learning (curriculum learning supported),' which clearly states the action and resource. It distinguishes from siblings by emphasizing 'staged' and 'RL,' separating it from sampling and transfer learning tools.

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 gives explicit usage guidance: 'Call reinvent_rl_scoring_design_guide first to collect scoring config interactively,' and clearly explains launch=True vs launch=False behavior, along with dry_run and validation defaults. This tells the agent when and how to use the tool.

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