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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds value beyond that by disclosing the result cap ('up to 20'), return field set (name, description, price, allergen tags, deep-link URL), and the public-directory requirement.

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?

Three short sentences, front-loaded with the core action, then return shape, then prerequisite. No filler and nothing to trim.

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 no output schema, the description usefully enumerates return fields and the result cap, and it states the access prerequisite. It leaves locale and the limit default unexplained, which is a minor but real gap for a 4-parameter tool.

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 50%: only slug and query are documented in the schema, while limit and locale are not. The description's 'up to 20 matching products' loosely maps to limit's maximum of 20 but does not explain the default of 10 or the locale parameter, so it only partially compensates.

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 (Search) plus resource (products) and scope (inside a single restaurant by keyword). This clearly separates it from search_restaurants (cross-restaurant) and get_restaurant_menu (full menu retrieval).

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?

Provides a concrete prerequisite: the restaurant must be in the public directory, which is a real gating condition an agent needs. It doesn't explicitly name sibling alternatives such as get_restaurant_menu, so it stops short of the top score.

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