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

Annotations already cover readOnly, idempotent, and non-destructive. The description adds valuable context beyond annotations by explaining the data source ('real order history') and the fallback behavior ('falling back to the same category'). This helps an agent anticipate results even when no order history exists.

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?

Two sentences, front-loading the core behavior and immediately giving real-world use cases. Every word earns its place; no filler or redundancy.

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 is complete for a read-only, two-parameter tool with an output schema. It covers data source, fallback behavior, and typical intents. A minor gap is not stating whether 'limit' applies before or after fallback, but this is unlikely to mislead an agent.

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%: 'product' and 'limit' are both described in the schema. The description reinforces the meaning of 'product' as the anchor item but adds no new parameter semantics beyond the schema. Baseline 3 is appropriate.

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?

Description states a specific verb ('Products frequently bought together') and resource ('given product'), with concrete use cases ('what goes with this', 'customers also bought', cross-sell'). It clearly distinguishes itself from siblings like best_sellers and search_products by defining companion-product semantics.

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 gives clear context for when to use it (cross-sell and related-item scenarios) without explicitly naming exclusions or alternatives. It could be stronger by saying 'not for best-sellers or general search', but the use cases imply selection well.

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