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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so safety is covered. The description adds no behavioral context beyond that: it does not say how results are ranked, what happens when preferences match nothing, whether the result set is capped, or whether the catalog is limited to what is in stock.

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?

A single front-loaded sentence that names the resource first, then the driving inputs. No filler sentences, though the inline enumeration of examples makes it denser than necessary when the schema already contains examples.

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 five-parameter, one-required, read-only recommendation tool with full annotation coverage and no output schema, the description covers the semantics of four of five inputs and conveys the return shape ('picks'). Missing only any statement about how many or what kind of results come back.

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 schema already documents all five parameters with types, enums, ranges and defaults. The description's examples ('vanilla', 'oud', 'citrus') clarify intent for preferences but roughly duplicate the schema's own examples, and it omits the limit parameter entirely; with the schema doing the heavy lifting, baseline 3 is correct.

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 (get/pick) and resource (fragrance recommendations) and enumerates the signals that drive personalization. It is clearly distinguishable from generic search_fragrances, but never names a sibling or explains the boundary against find_similar, trending_fragrances, or what_to_wear_tonight.

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?

Usage is only implied: the listed inputs (preferences, budget, occasion, gender) suggest this is the tool for taste-driven discovery rather than lookup or comparison. There is no explicit when-to-use, when-not-to-use, or routing to the sibling tools that also surface fragrances.

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