log_meal

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

Annotations show readOnlyHint=false and no other safety hints, so the description carries the behavioral burden. It fully discloses important behaviors: never overwriting known stored macros with fresh estimates, requiring confirmation before force=true, handling duplicate errors by prompting the user, and letting the server decide whether hydration tracking is enabled.

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 long, but its complexity warrants it: 11 parameters, macro resolution rules, duplicate handling, and hydration all need explanation. It is well-organized with clear section headers and fronts the core purpose before diving into edge cases, though a more compact phrasing would slightly improve conciseness.

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's complexity, the description is remarkably complete. It covers inference rules, macro sourcing, required fields, fasting, duplicates, and hydration, leaving no major decision ambiguous. An output schema exists, so the absence of explicit return-value details is not a gap.

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?

Despite 100% schema coverage, the description adds substantial meaning beyond the schema: date inference rules, canonical meal_type time mapping, when recipe_name supplies macros, how fluids and alcohol_g interact, and the explicit rule to never call without all four macros populated. This goes far beyond what the input schema alone conveys.

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 a specific verb and resource: 'Log a meal to the user's food diary,' and expands with concrete trigger conditions ('mentions eating, describes a meal, or asks to log food'). It covers special cases like fasting and drinks without blurring the core purpose, and it is clearly distinguishable from siblings like update_meal and list_meals.

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 gives detailed when-to-use guidance: direct meal logging, repeats, saved recipes, brand names, fasting days, and drinks/hydration. It explicitly names alternatives such as list_meals for repeats and update_meal for correcting duplicates, and it states this is the single write path for drinks, clearly routing behavior away from other tools.

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