fda_food_recalls

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

Annotations include readOnlyHint: true, so the safety profile is already known. The description adds domain context by explaining the severity classes and provides query examples, but does not disclose additional behavioral traits such as pagination limits, rate limits, or result structure. This is similar to the mid-tier example where annotations cover the core and description adds modest extras.

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 compact and front-loaded with the main purpose. Every sentence serves a purpose: defining the tool, explaining classification levels, and offering immediately actionable examples. There is no redundancy or fluff, making it highly efficient for an agent to parse.

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 simple search tool with two parameters and no output schema, the description covers the core usage well. It explains the classification system and gives example queries, which is sufficient for basic invocation. However, it does not mention how results are returned or note any limitations, leaving a small gap for a complete picture.

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 both 'search' and 'limit' having descriptions. The tool description adds value beyond the schema by providing concrete field examples (classification, recalling_firm, reason_for_recall) that are not listed in the generic schema description for the search parameter. This enriches the agent's understanding of how to construct queries.

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 clearly states the tool searches FDA food recall enforcement reports, using a specific verb ('Search') and resource ('FDA food recall enforcement reports'). It also defines recall classification levels (Class I, II, III) and provides example queries that reinforce the scope, distinguishing it from other FDA recall tools like fda_drug_recalls.

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 clear context for use through example searches (e.g., by classification, firm, reason), but does not explicitly mention alternatives like fda_drug_recalls or fda_device_recalls. It implies the food-specific scope via the name and title, but lacks an explicit when-not-to-use statement.

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