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

Annotations cover the safety profile (readOnly, non-destructive, openWorld, idempotent), but the description adds real behavioral context: ideas rotate daily, weight-loss requests yield lighter filling ideas at 450 calories or less and omit shop links. It's strong disclosure, though it never describes the shape of the response beyond 'rough macros' and shop links.

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?

Front-loaded with purpose, then examples, then boundaries, all in a compact block. It loses a little economy by re-listing the goal/diet/meal values that the schema already enumerates, but every sentence otherwise carries usable information.

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 compensates by explaining what comes back (rough macros, shop links) and how special cases behave (rotation, weight-loss mode, no shop links). Combined with full schema coverage and safety annotations, an agent has everything needed to call it correctly.

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 six parameters are already documented with their defaults and allowed values. The description mostly restates the goal/diet/meal enumerations the schema already contains and only lightly clarifies intended use of q and country. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (get) and resource (simple meal ideas) plus the axes that shape the result (goal, diet, meal, rough macros). This is clearly distinct from the sibling nutrition-lookup tools (get_food_nutrition, get_barcode_nutrition), which fetch data rather than generate suggestions. An agent can route to it without opening the schema.

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?

Gives concrete triggering phrasings ('high protein halal dinner idea', 'a quick vegan lunch'), enumerates the valid goal/diet/meal values, and explains the q escape hatch for free-form input. It also states the exclusion: no calorie/weight targets, plus the specific weight-loss fallback behavior and a doctor/dietitian pointer.

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