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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that: the preference for live order-history data with a curated fallback, the degraded 'guidance' mode when no parameter is passed, and the non-pressuring tone constraint. Return format and how many results are guaranteed are not specified.

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?

Front-loaded with the core action and the two data-source modes, then the exclusion parameter, then the tone note. Slightly repetitive — 'NON-pushy' and 'Never pressure — helpful suggestions only' say the same thing twice — but every other clause carries distinct operational information.

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?

With zero required parameters and no output schema, the description has to explain the three calling modes and it does so clearly, including the empty-argument path. It stops short of describing what a suggestion result contains beyond 'companions with a reason'.

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 each property is already documented, so the baseline is 3. The description still adds relational meaning the schema does not: that `product` is preferred over `use_case`, that `use_case` is a fallback rather than an independent filter, and that `already_have` is a suppression list.

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?

States a specific verb (suggest) and resource (add-on products) with the qualifier 'NON-pushy' and '1–2 genuinely useful companions with a reason', which makes the output shape legible. It does not distinguish itself from the sibling vivid_recommend, which sounds like an overlapping recommendation tool, so an agent cannot fully route between them from the text alone.

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?

Gives explicit conditional usage: pass `product` to use real order-history data, pass `use_case` as the curated fallback, omit both for guidance, and pass `already_have` to suppress items the customer chose. What is missing is a when-not-to-use statement or a comparison to vivid_recommend, the obvious alternative.

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