health_log_meal

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

Annotations already declare idempotentHint=true and destructiveHint=false, so safety is partly covered. The description adds genuine behavioral detail: missing nutrition values are not zero-filled, and anonymous foods cannot be updated after insertion (a notable immutability trait). It omits the dry_run preview-by-default behavior, which is central to calling this 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?

Three tight clauses with the purpose front-loaded and no filler. Efficient and on-point, though arguably over-terse given the tool's complexity.

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 an 11-parameter mutation tool with no output schema, the description is thin. It never mentions dry_run defaulting to preview-only (the single most important fact for an agent to invoke correctly), nor the timezone/idempotency semantics needed for safe writes. The description leaves significant gaps in the calling contract.

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 36%, so the description must compensate. It clarifies that nutritional values (fat_g, carbs_g, protein_g, calories_kcal, servings) are optional and not padded, but says nothing about dry_run, meal_type, the two timestamps, or idempotency_key beyond what the schema already documents. Partial compensation only.

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+resource: 寫入飲食紀錄 (write a meal record). This clearly distinguishes it from health_log_workout (logging exercise) at the resource level, though no sibling is named explicitly. Purpose is unambiguous.

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?

No when-to-use vs when-not guidance and no routing to alternatives among the many health_* siblings (create/update/get/list). Notes that nutrition values may be omitted but provides no context about when this tool should be chosen over health_create or health_log_workout.

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