Sweep a seed range

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

Annotations only declare readOnlyHint=true, so the description carries behavioral disclosure. It adds valuable details: aggregation is computed server-side, per-run event logs are not returned, and max count is 1000. No contradiction with annotations.

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?

Two dense sentences plus a short max-count clause, with the operation and scope front-loaded. No filler; every sentence contributes to selection or invocation.

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?

For a batch-analysis tool with no output schema, the description enumerates the return aggregates in detail and clarifies the no-logs constraint. It is sufficient for an agent to decide and call correctly, though it doesn't describe error handling or exact output structure, which is acceptable given the schema richness elsewhere.

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 100%, so the baseline is 3. The description adds the seed-range formula and restates max count, but parameter-level meaning is already well documented in the schema, including mode explanations and featured seed examples.

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 states a specific verb ('Run'), resource ('count consecutive seeds'), scope ('under one configuration'), and output ('aggregate statistics only'). It enumerates the exact statistics returned and explicitly notes that per-run event logs are not returned, which differentiates it from run_engagement without needing to open 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 gives clear context: run a batch of seeds and get only aggregate statistics. It routes to run_engagement for notable seeds and states that per-run logs are absent, implying when to switch. It doesn't explicitly cover compare_configs, describe_model, or get_config_schema, but the primary use case is well defined.

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