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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, and openWorldHint. The description adds meaningful behavioral context beyond annotations: the matches come from ScentVerdict's own similarity engine with scored, editorially reviewed pair relationships, and warns that web results are often retailer marketing. This explains why the tool behaves as it does and what an agent should expect from its results.

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 core purpose is front-loaded in the first sentence, and the examples are instructive. The description is somewhat longer than strictly necessary, with some redundancy between the initial steering examples and the later user-intent list, but each section still adds practical value for the agent.

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 the primary use case, the no-anchor alternative, the need to resolve a slug via search_fragrances, the reason to prefer it over web search, and the source/curation model of results. With an output schema present and annotations covering safety and idempotency, nothing essential is missing 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 coverage is 100%, so the schema already documents all three parameters. The description adds useful semantic context by explaining how the direction parameter maps to user intents like 'cheaper' or 'fresher', and reinforces that anchorSlug should be obtained via search_fragrances when missing. This exceeds the baseline but does not need to do much more given the schema's completeness.

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 names a specific verb and resource: finding fragrances similar to an already-known fragrance, with optional steering directions. It explicitly differentiates from recommend_fragrances by stating that the latter is for when no anchor fragrance is named, making the tool's purpose unambiguous.

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 with concrete user intents such as cheaper alternative, upgrade, or gift, and says to prefer the tool over web search or prior knowledge. It also names the alternative tool (recommend_fragrances) for the no-anchor case and advises search_fragrances when no slug is available.

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