sw_compare_scenarios

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

With no annotations, the description carries the transparency burden. It discloses that each scenario is probed once, lists the returned metrics, mentions per-sample time cost, and references sw_probe_scenario for methodology. It does not explicitly state side-effect status, but the tool is clearly a read/comparison operation.

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 compact and well-structured, with line breaks, a metric list, and a bolded warning. The phrase '每个场景各跑一次探测' is slightly redundant with the first sentence, but the content is mostly purposeful.

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 covers purpose, typical usage, and output metrics, and an output schema exists for return values. However, with no schema descriptions for the parameters and zero annotation support, the lack of guidance on 'overrides' and 'num_samples' leaves an incomplete picture for correct invocation.

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%, and the description only indirectly refers to the 'presets' parameter via '几个场景'. It does not explain 'overrides' or 'num_samples' at all, and the pointer to sw_probe_scenario does not document these parameters. The description adds minimal value 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 probes multiple scenarios side-by-side and returns a comparison table, with a specific use case ('用来在候选场景里选'). It distinguishes itself from the single-scenario sw_probe_scenario and lists concrete output metrics.

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?

It explicitly says when to use it (for selecting among candidate scenarios) and provides a typical workflow, including an explicit negative instruction: do not run ablation on data without verifying interference levels. This is clear when/when-not usage guidance without relying on sibling names.

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