Create a private recipe

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

Annotations only tell the agent this is a non-read-only, non-destructive, non-idempotent call. The description adds real behavioral detail beyond that: privacy (user-only, no shared catalog), atomic validation semantics ('when one is wrong, nothing is created and the error names it as ingredients[index]'), the return payload, and the fact that each call creates another recipe with a specific retry path.

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?

Front-loaded with the core action and privacy constraint, and nearly every clause carries information (atomicity, return shape, logging pattern, idempotent retry). It is a dense single block with some long compound sentences, which costs a little readability but no meaningful waste.

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?

With an output schema present the description needn't explain returns, yet it still names recipe_id and per_serving fields. Combined with full schema coverage, annotations, and explicit cross-tool workflow steps, an agent has everything needed to call this correctly on the first attempt.

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 already 100%, so the baseline is 3, but the description adds genuine meaning: ingredients take 'food_id, quantity and unit or measure_id as add_food does', must be a PRODUCT, and validation errors reference ingredients[index]. It clarifies the unit-vs-measure_id relationship in prose rather than just per-field text.

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 ('Save a private recipe') plus the scope ('in the user's own foods from catalog products... never goes to the shared catalog'). This clearly separates it from create_food and update_recipe/delete_recipe without needing to open any schema.

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?

Gives explicit usage context ('so it can be logged as one food'), tells the agent how to consume the result ('Log it with add_food: food_id recipe_id, food_type RECIPE, quantity the servings eaten'), and provides precise retry/exclusion guidance ('when one fails with anything but a validation, not_found or rate_limit error, look for it with get_my_foods before creating it again').

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