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

Annotations already establish readOnly/idempotent/non-destructive, so the description's contribution is the added semantics: default behavior excludes sold-out and closed offers, and the order model means orders are requests the cook must confirm rather than confirmed purchases. That last point is genuinely useful behavioral context not present in the annotations. It does not discuss auth requirements or response size/pagination, keeping it below 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?

Two sentences, front-loaded with the core purpose and then the output contents; nearly every clause carries information. The first sentence is a long run-on enumeration, which slightly hurts scannability but wastes no words.

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 an output schema present, the description needn't restate return shapes, yet it still gives a useful summary of what comes back and clarifies the default availability filtering and the request-based order model. For a read-only, three-parameter tool this is close to complete; only guidance on the week parameter and sibling selection is missing.

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%, so all three parameters (week, kitchen, include_unavailable) are already documented in the schema, which sets the baseline at 3. The phrase 'can be ordered now' weakly implies the include_unavailable default, but the description never explains the week filter or the kitchen slug/link forms, so it adds little beyond the schema.

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 and resource ('Returns one kitchen's menu') and enumerates the payload precisely: dishes, meal packages, prices, dietary tags, stock, cutoff, pickup/delivery times, quantity rules, required options, payment methods, and order model. That enumeration makes it clearly distinct from siblings like get_pickup_windows or search_kitchens without needing to name them.

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 only implied — the agent can infer this is the lookup to call before build_order_link, but the description never says when to use this versus search_kitchens or get_pickup_windows, nor does it state any preconditions or exclusions. The 'orders are requests the cook confirms' line is contextual, not usage guidance.

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