log_custom_food

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

With no annotations, the description carries the full burden and does it well: it explains meal-time window matching, SNACKS fallback, ID format differences between sources, and the 400 error on source mismatch. This is concrete behavioral context beyond the schema.

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 well organized with an opening summary, source bullets, and an Args list. Every section adds value and the most important scoping behavior is front-loaded.

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 6-parameter tool with zero schema descriptions, the description covers all inputs, sources, defaults, time handling, and error behavior. Since an output schema is present, not detailing return values is acceptable.

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 0%, and the description compensates fully: it documents every parameter with formats (YYYY-MM-DD, HH:MM:SS), source-specific semantics, defaults for serving_qty and source, and where to obtain food_id/serving_id.

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 opens with a specific verb and resource ('Log a food item to a meal on a date') and clarifies it adds a food entry to the nutrition log. It does not explicitly distinguish itself from the sibling log_food, so it loses the last point on differentiation.

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?

Provides clear guidance for choosing between GARMIN and FATSECRET sources and points to get_custom_foods/search_foods for IDs. However, it never states when to use this tool instead of the similar sibling log_food or what conditions make this tool inappropriate.

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