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

Annotations already establish read-only, non-destructive, closed-world behavior, and the description adds substantial context on top: the provenance of every calorie/macro value (USDA FoodData Central, Open Food Facts, user entry, AI estimate), the fact that values are approximate and not batch- or package-specific, and an explicit prohibition on medical use such as insulin dosing or glucose prediction. This is exactly the kind of behavioral disclosure annotations cannot carry.

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-loads the purpose, then mode details, then the filter interaction, then the safety caveat — a logical progression with no filler. The disclaimer is long but every clause (provenance, approximation, medical unsuitability) earns its place for a nutrition tool.

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?

Given a single optional enum parameter, an existing output schema, and annotations covering the safety profile, the description supplies everything an agent needs: what each mode returns, how the filter applies, and the reliability limits of the data. Nothing material 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 coverage is 100%, so the `meal` enum is already documented as 'Only foods logged under this meal.' The description adds real meaning beyond that by clarifying the filter applies to BOTH the usual and recent lists, which the schema alone does not convey. Baseline 3 is exceeded but no format or default nuance is added.

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 (read what the user usually/recently eats) and cleanly splits the tool into two named modes, `usual` and `recent`, with the exact fields each returns. It does not, however, distinguish itself from siblings like search_foods or get_day, so an agent must infer the boundary from the mode semantics alone.

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 description makes the trigger conditions for each mode implicit but clear: `usual` for most-logged foods, `recent` for the last seven days, and `meal` to narrow either. There is no explicit when-not guidance or named alternative (e.g., when to prefer search_foods or get_range), so usage is inferred rather than stated.

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