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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds two pieces of real value beyond that: the public-directory precondition and the returned field set (name, description, price, allergen tags, deep-link URL). It omits what happens when the restaurant is not public (error vs empty result) and whether results are ranked.

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 tight sentences: the operation and its scope come first, then the return shape and the precondition. Nothing is redundant and nothing needs re-reading.

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 correctly takes on the burden of describing return values, and it does so at a useful level of detail while also flagging the public-directory constraint. The remaining gaps are the undocumented locale parameter and undefined behavior on a non-public or unknown slug.

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%: slug and query are documented in the schema, limit and locale are not. The description reinforces the slug scoping ('inside a single restaurant'), the query semantics ('by keyword'), and the result cap ('up to 20'), but it never mentions the locale parameter or how it affects matching. This is the expected baseline for a half-documented schema, with marginal added meaning.

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 states a specific verb and resource ('Search products') plus a hard scope constraint ('inside a single restaurant by keyword'), which separates it from the catalog-wide search_restaurants and from browse-style siblings like get_restaurant_menu. It stops short of naming any sibling explicitly, so the differentiation is inferable rather than stated.

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 implied by the scope sentence and one prerequisite is given ('Restaurant must be in the public directory'), which is genuinely useful. However, there is no explicit when-to-use/when-not guidance and no routing to alternatives such as get_restaurant_menu for browsing the full menu versus keyword search.

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