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

Annotations cover read-only/open-world/no-idempotency, and the description adds genuinely non-structured information: each call is charged USDC from a configured wallet, capped by session/daily budgets, the confirm_over_cap escape hatch, and an explicit prompt-injection warning that results are third-party data, not instructions. It does not explain pagination or why the operation is non-idempotent, which is why it is not a 5.

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?

The key facts (what it is, product areas, paid model, safety caveat) are front-loaded before the dense per-product list, and the bullets are terse. The product lines are somewhat compressed and truncated, but there is little filler.

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 covers return content (dishes, prices, section, portion, currency, distance, scrape date), cost model, and the budget-confirmation flag, which is most of what an agent needs. What is missing is how this tool relates to call_product/food_coverage and full parameter detail on the truncated product entries.

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?

Because the params property is a free-form object with additionalProperties=true, the schema itself documents zero individual parameter names; the description is the only source for restaurantId, lat/lon/radiusKm/limit/type, country/area, and defaults (2 km default, 10 km max). That is substantial added meaning, though the per-product strings are truncated so some parameter detail is lost.

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 opening sentence gives a concrete resource (restaurants and their menus, scraped dishes/prices with scrape date) and a scope (near a point or in a ski area). It is clear what the tool returns, but it does not distinguish itself from the sibling call_product dispatcher, which appears to offer the same product-based invocation pattern.

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 per-product entries do imply when each product applies (one restaurant's menu, radius search from lat/lon, all venues in a ski area), which is useful routing. However, there is no guidance on when to pick this tool over call_product or food_coverage; 'Areas: food_coverage (free)' is stated cryptically without explaining the relationship or the when-not case.

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