Log Food (diary write)

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

Beyond the annotations, the description reveals mutation, side effects ('Tags companions on the mirrored event', 'Rebuilds life_state'), alias resolution behavior, unknown-name tolerance, and authentication constraints ('Requires API key or OAuth... Share tokens cannot write'). These are meaningful behavioral facts not inferable from readOnlyHint/destructiveHint alone.

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?

Every sentence earns its place: mutation warning, trigger condition, worked example, optional fields, side effects, auth limitations, and pricing. The key information is front-loaded and the later sentences are short and scannable.

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 15-parameter mutating tool, the description, combined with a rich input schema and output schema, is complete. It provides a worked example, side-effect model, authentication requirements, and enough parameter semantics to make a correct call without additional inference.

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 87%, so the schema already documents most parameters. The description adds real value by mapping an utterance to what/kind/meal_period/with, noting the optional place/merchant/amount/consumed_at fields, and explaining alias resolution and non-failure for unknown names.

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?

Description opens with 'MUTATES the authenticated user Food Diary and calendar,' naming the exact action and resource, then supplies a concrete natural-language example. The title '(diary write)' plus 'Use when they ate or drank' clearly separates it from sibling tools like log_event and update_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?

Explicitly states 'Use when they ate or drank — do not store this as a chat memory,' giving both a positive trigger and a negative instruction. It does not directly name sibling alternatives such as log_event, update_food, or delete_food, but the food/meal trigger makes the intended selection clear.

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