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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds value by disclosing that comparisons are computed from ScentVerdict's structured note data rather than assembled from reviews, and by enforcing the exactly-two constraint. This goes beyond what the annotations alone provide, though it does not discuss output shape or edge cases.

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 three sentences with strong front-loading: the core behavior comes first, followed by usage context and the sibling alternative. It avoids boilerplate and every sentence serves a distinct purpose, with only minor redundancy between 'own note data' and 'computed from structured data'.

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 low parameter count, an output schema, and annotations that already establish the safety profile, the description is complete. It tells the agent what the tool does, when to use it, what data it draws on, and which sibling to choose instead, leaving no important decision ambiguous.

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%, and the schema already documents both slug parameters. The description does not elaborate on slug format or how to obtain slugs, but the schema's brief descriptions are sufficient for this simple parameter set. Baseline 3 is appropriate because the schema does the heavy lifting.

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 ('compare'), a constrained resource ('exactly two fragrances'), and the concrete outputs ('which notes they share, which differ, and both editorial verdicts'). It also distinguishes itself from find_similar_fragrances, preventing confusion among the sibling 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?

It gives explicit when-to-use guidance ('whenever the user is choosing between two named fragrances...') and explicit when-not-to-use guidance ('Use find_similar_fragrances instead when they want alternatives...'). It also advises preferring this over web search, which helps the agent select among broadly similar capabilities.

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