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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real context beyond them: the underlying data source (FDA Total Diet Study), the fact that recalls and drinking-water notes are folded into the result, and that named products are ordered highest-median-first. It does not discuss failure behavior for an unrecognized chemical name.

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?

It is a single dense sentence with no filler, front-loading the input ('for one contaminant') before the output contents. The enumerations are long, but each item (return payload components) earns its place. Slightly heavy as one unbroken clause chain, but not bloated.

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 no output schema, the description carries the full burden of explaining return values, and it does so thoroughly: sample counts, detections, averages, years, named products ordered by median, recalls, and a drinking-water note. It is complete for a one-parameter lookup; only the behavior for an invalid or unsupported chemical name is unaddressed.

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 coverage is 100%, so the baseline is 3. The description goes further by enumerating valid chemical values and families (including slug-style examples like dehp, dbp, deht, bpa) and making clear the field is a single contaminant, which reduces the chance of passing a list or an out-of-vocabulary name.

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 names a specific verb and resource ('returns the everyday foods where FDA's Total Diet Study found the highest typical levels' for 'one contaminant'), and enumerates the accepted chemical families (lead, cadmium, mercury, arsenic-total, perchlorate, phthalates, substitutes, bisphenols). This is clearly distinct from the sibling set (additive_status, check_product, compare_products, food_category, interpret_test_result), none of which are contaminant-source lookups.

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 implied by the exhaustive description of what is returned, which tells an agent what question this answers. However, there is no explicit when-to-use framing, no exclusions, and no pointer to a sibling for related questions (e.g., product-level testing vs. category-level sourcing). Minimum viable guidance only.

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