NutriBalance

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

Annotations declare read-only, non-destructive, idempotent properties. The description adds valuable output context ('breakdown by category, a letter grade, and actionable recommendations') since no output schema exists. Does not mention calculation methodology or error conditions, but covers the critical gap of return value structure.

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?

Three sentences, zero waste. Front-loaded with core functionality (calculation and range), followed by output description, then usage conditions. Every clause provides distinct information (scope, inputs, outputs, use-cases).

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 9-parameter tool with no output schema, the description adequately compensates by outlining the three components of the return value. Good annotations cover safety profile. Minor gap: does not specify the structure/format of the 'breakdown' object or recommendation list.

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?

With 100% schema description coverage (baseline 3), the description adds semantic grouping by categorizing inputs as 'macros' (calories, protein, carbs, fat) and 'optional micronutrient data' (fiber, vegetables, water), helping agents understand parameter relationships beyond the schema's flat list.

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?

Excellent specificity: states the exact calculation (nutrition quality score 0–100), inputs (macros, optional micronutrient data), and deliverables (breakdown, letter grade, recommendations). Clearly distinguishes from siblings like generate_meal_plan (planning) and lookup_nutrition (food lookup) by focusing on evaluating existing intake.

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?

Provides explicit positive guidance ('Use this when someone wants to rate their diet, check if they're eating well, or get feedback on a day's meals') covering three distinct use cases. Lacks explicit negative constraints ('do not use for...') or named sibling alternatives, preventing a 5.

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