Sweep a seed range

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

The description aligns with the readOnlyHint annotation, stating that only aggregate statistics are returned and per-run event logs are not. It adds transparency about server-side aggregation and the max count. No contradictions.

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, well-structured paragraph that front-loads the main action, enumerates the returned statistics, notes exclusions, and gives a constraint. Every sentence adds value without redundancy.

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?

Given the absence of an output schema, the description comprehensively lists the returned aggregate statistics (win rates, distributions, stalemate reasons, notable seeds). It also addresses the config_overrides parameter and directs to get_config_schema for details, ensuring an agent has sufficient context to use the 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?

Schema coverage is 100% (all parameters documented), so baseline is 3. The description adds value by explaining the seed range as 'start_seed .. start_seed+count-1' and advises calling get_config_schema for config_overrides details, which enhances understanding beyond the schema.

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 clearly states the tool runs consecutive seeds under one configuration and returns aggregate statistics. It specifies the action (sweep seeds), resource (seed range), and output (aggregate stats). It further distinguishes itself from sibling run_engagement by noting that notable seeds can be explored with that tool.

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 explicitly indicates when to use this tool (for aggregate statistics over multiple seeds) and when to use run_engagement (for drilling into notable seeds). It also mentions the max count constraint, guiding appropriate usage.

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