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

Annotations provide readOnlyHint=true, and the description does not contradict it. The description adds substantial behavioral details beyond annotations: per-portion scaling mechanics, the meaning of unit='serving', the default per-100g basis, and the effect of omitting quantity. These are valuable behavioral specifications an agent needs to call correctly.

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 description is a single, logically organized paragraph that front-loads the primary purpose and then layers supporting details: scaling, serving, and nutrient filtering. Every sentence conveys useful information without fluff. It is slightly longer than necessary but remains tight given the breadth of behavior covered.

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, single-food retrieval tool, the description is remarkably complete. It covers the return scope, filtering, scaling semantics, serving interpretation, and default behavior. It points to the correct sibling for ID discovery and implicitly differentiates from plural retrieval. There is no missing critical information for an agent to invoke correctly, especially with a rich output schema available.

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 all parameters are described in the schema. The description enriches these with practical semantics: fdcId discovery via search, quantity/unit scaling requirements, 'serving' behavior, and nutrient ID lookup via usda_list_nutrients. It goes beyond the schema's mechanical descriptions to explain usage context.

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: 'Get the full nutrient profile for one food by FDC ID.' It clearly distinguishes from siblings like usda_get_foods (plural) by emphasizing 'one food' and mentions the optional filtering via nutrients[]. The primary function is unambiguous and stands apart from search, list, and compare tools.

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?

Explicitly routes to usda_search_foods for discovering FDC IDs and explains when to use nutrient filtering to reduce response size. It does not explicitly mention when to prefer usda_compare_foods or usda_get_foods, but the singular-versus-plural distinction is implicit. Missing explicit exclusions, but the core usage is well-defined.

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