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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's added value is the match semantics and the shape of results (macros per portion). It does not state whether results are capped or paginated, but the core behavior is disclosed.

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 short sentences with no filler, and the scope statement comes first. The phrase "Foods from the TACO table and the trainer's own" is slightly elliptical but still readable.

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?

For a read-only, two-parameter search with no output schema, the essentials are present, but result limits, pagination, and empty-match behavior are unaddressed, and the "recipe" source remains unexplained.

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 only 50%, and the description partially compensates: it explains that multiple words are ANDed, which is genuinely beyond the schema, and it hints at source values. But the source enum's third value, "recipe", is never mentioned or reconciled with the description's two origins, leaving one parameter's semantics incomplete.

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 identifies the resource precisely, including the two data origins (TACO table and the trainer's own foods) and that macros are returned per portion. It does not explicitly name alternatives such as list_favorite_foods or search_exercises, so sibling differentiation relies on the tool name.

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?

"Each word must appear in the name" implies the search is an AND-of-terms lookup, which is useful implied usage context. However, there is no explicit guidance on when to choose this over list_food_categories or list_favorite_foods, nor when to set the source filter.

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