gauge_compare

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

No annotations are provided, so the description carries the transparency burden. It discloses the return value structure (overall_verdict and per-metric comparison results), which is useful behavioral information. However, it does not mention any side effects, prerequisites, or error conditions, though for a comparison tool these may be less relevant.

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, concise sentence that states the core action and return value without redundancy. It earns its place with no filler.

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 tool's simplicity and the absence of an output schema, the description provides the essential purpose and return value information. However, it lacks any mention of prerequisites (e.g., traces must exist) or potential error conditions, leaving it slightly incomplete for agents that need to anticipate failures.

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?

The input schema provides full Japanese descriptions for both required parameters, covering 100% of the parameters. The description adds no extra parametric meaning beyond restating the comparison context, so it doesn't improve on 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 that the tool compares a baseline trace with a new execution trace to determine metric improvement/deterioration, and specifies the return value includes overall_verdict and per-metric results. This distinguishes it from sibling tools like gauge_lint or gauge_report, which serve different purposes.

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 does not explicitly mention alternative tools or exclude use cases, but the comparison purpose is clear from the tool name and description. It provides context that this is for comparing traces after changes, which is implied by the parameter names and descriptions.

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