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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds useful behavioral context about what data is returned (reactions, outcomes, demographics) and notes the US public domain source. This adds value beyond the annotations without contradicting them.

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?

Four sentences with all essential information: purpose, return fields, filter example, and distinction from recall tools. The structure is efficient and front-loaded, though the source note could be seen as slightly less critical. No wasted words.

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 search tool with an output schema present, the description covers the core aspects an agent needs: what data is searched, what fields are returned, how filtering works with examples, and how it differs from recall tools. Pagination and default behavior are documented in the parameter descriptions, so nothing critical is missing.

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% with all three parameters documented, so a baseline of 3 is appropriate. The description goes further by providing concrete Lucene syntax examples with real field names like products.industry_name and reactions, which helps the agent construct valid search expressions.

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 states a specific verb ('Search') with a clear resource (FDA CAERS database of consumer-reported adverse events for foods and dietary supplements), lists the return fields (reactions, outcomes, product names, demographics), and explicitly distinguishes itself from recall enforcement. An agent can accurately understand what this tool does and how it differs from recall-focused tools.

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 clear context for when to use this tool (searching consumer-reported adverse events for foods/supplements) and explicitly separates it from food recall enforcement (health.food_enforcement). It also demonstrates Lucene filter syntax. However, it does not mention other adverse-event siblings like drug or device adverse events, leaving some potential ambiguity.

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