log_food

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

Annotations cover the safety profile (not read-only, not destructive, open-world), and the description adds substantial context beyond them: the subscription gate, the mealId dependency, the resulting 400 'mealId must not be null' error, and the fact that a clearer error is thrown first. The meal/time resolution rules are also disclosed. It loses a point because the final sentence is truncated ('it picks a time that…'), leaving that behavior unexplained.

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 subscription requirement and endpoint are front-loaded, which is good. However the text is dense and run-on, mixing API mechanics, defaults, and error behaviors in long sentences, and it terminates mid-sentence, so structure and completeness of thought suffer.

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 write tool with a nested object parameter and no output schema, the description supplies the prerequisites, error conditions, default-resolution logic, and notes the return value ('the whole day's log'). The truncated ending is the main gap, but overall it is close to complete for correct invocation.

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?

Top-level schema coverage is 0% and the single parameter is a nested object, so the description carries the burden. It compensates well by spelling out the FoodLogInput shape, naming fields not described in the schema (foodId, servingId, regionCode, languageCode), giving defaults (servings=1, source='GARMIN'), and explaining that the catalogue food's source/regionCode/languageCode should be passed for a search result.

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 ('log food'), names the exact endpoint (PUT /nutrition-service/food/logs), and specifies that it logs one REGULAR_LOG item and returns the whole day's log. It is distinguishable from get_nutrition_daily_food_log and delete_food_logs, though it never explicitly contrasts with the close sibling quick_add_food.

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 an important prerequisite (requires Garmin Connect+ subscription, check with has_connect_plus) and warns that a mealId from in-app nutrition setup is required. However, it gives no guidance on when to choose this over quick_add_food or create_custom_food, so routing between logging options is left to inference.

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