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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered. The description adds only that replacement is possible; it does not say whether replacing wipes all prior items, what permissions are needed, or that partial item failures are tolerated (that detail lives in the items schema, not the description).

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?

A single front-loaded sentence with the resource definition nested inline; nothing is wasted. Slightly convoluted grammar ('Creates one of the person's favourite dishes, a named set of foods logged together, or replaces...') makes the create/replace parallelism a little harder to parse than it needs to be.

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 all six parameters optional, 100% schema coverage, and an explicit destructive annotation, the description supplies enough to know this is a create-or-replace dish mutation. It omits that name is effectively required for creation and that entry_id substitutes for items, but the schema carries both, so the gap is minor.

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 100%, so every parameter, including the dish_id/items/entry_id interplay, is already documented in the schema. The description restates the dish concept and replacement but adds no syntax, format, or precedence rules beyond what the schema provides.

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 ('Creates') and a well-defined resource ('a named set of foods logged together') and covers both the create and replace modes in one sentence. It implicitly distinguishes a dish from a single food (save_food) and from a diary entry (log_meal), but never names those siblings, so the differentiation is inferential rather than explicit.

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?

The 'or replaces an existing one' clause hints that the mode is chosen by whether a dish already exists, and the schema makes the dish_id switch explicit, but the description never states when to use this versus save_food or log_meal. Usage is implied rather than guided.

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