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

Beyond the readOnlyHint annotation, the description discloses that allergies are self-reported and not a safety guarantee, mentions the returned allergy_disclaimer, notes the limitation of the allergen scope, and clarifies that dislikes are taste preferences—not safety exclusions. This richly supplements the annotation.

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 description is front-loaded with the core purpose and then layers critical warnings in a structured, readable way. Every sentence serves a purpose—either defining functionality or providing safety-critical guidance—making the length justified and efficient.

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?

Given the tool has no output schema, the description compensates by listing the returned fields (diet style, allergies, dislikes, portion note) and includes the allergy_disclaimer. It also covers usage constraints and safety limitations, making it complete for an agent to invoke and interpret results correctly.

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?

There are zero parameters, so the description has no need to explain inputs. Baseline is 4. The description does not waste space on parameter details, as none exist.

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?

The description opens with 'Read the user's saved dietary preferences', a specific verb+resource pair, and enumerates the contents (diet style, allergies, dislikes, portion note). This clearly distinguishes it from sibling tools like get_day or get_pantry, which focus on logs and inventory.

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 description states when to use the tool: 'so you can tailor logging and suggestions WITHOUT re-asking every chat'. It also gives explicit exclusions, such as asking about allergens outside the big-9 and never treating dislikes as allergies, plus instructs to always direct users to check labels.

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