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

Annotations already declare this a safe, read-only, open-world lookup, so the description's job is to add context beyond that — and it does, disclosing a 2-credit cost and that micronutrients and derived intelligence (calories per gram, macro share of calories) are gated behind paid plans. That tier-dependent output variation is exactly the kind of behavior an agent can't get from the annotations. It stops short of describing failure behavior or partial results.

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?

One front-loaded sentence carries the core read, the data source, the scaling basis, the paid-tier extras, and the cost in a trailing parenthetical. The leading "Nutrition: Nutrition" restatement is the only redundancy and costs almost nothing.

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?

Return values need not be spelled out given an output schema exists, yet the description still usefully summarizes free vs paid payloads. For a two-parameter lookup this is nearly complete; only the unknown-food/error case and the generality limit of the food name are left unstated.

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 both parameters are already documented, including the per-100-gram default for `grams`. The description's "per 100 grams straight from the USDA" restates rather than extends that, and adds no syntax guidance (e.g. format for compound names like "chicken breast"). Baseline 3 applies.

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 uses a specific verb and resource ("returns the nutrition facts for a generic whole food by name") and scopes the data source (USDA food composition database) plus the unit basis (per 100 grams). It doesn't name or contrast any sibling tool, so the agent must infer that this is the food-nutrition lookup rather than, say, RecipeGenerator or PeriodicTable.

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?

Usage is only implied: look up a food by name when you need nutrition data. The qualifier "generic whole food" usefully signals that branded or packaged products are out of scope, but no alternative tool or when-not condition is stated, and nothing says what happens for unrecognized foods.

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