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

Annotations already establish readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description adds meaningful context beyond annotations: recall records are correction/removal actions and do not alone prove patient harm. This is valuable interpretive context, though it doesn't disclose pagination or rate limits, which are largely covered by schema and output schema.

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 two short sentences, clearly front-loaded with the core action and search fields, followed by a vital caveat. Every word adds value; there is no redundancy or fluff.

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?

Given the tool has 7 parameters all fully documented in the schema, an output schema, and robust annotations, the description only needs to convey the high-level purpose and any interpretive caveats – both of which it does. It provides enough context for an agent to select it appropriately among many FDA device siblings.

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 each parameter described (e.g., 'Recalling firm substring', 'Product or reason text'), so the baseline is 3. The description lists the fields but does not add significant new meaning beyond what the schema already provides; it merely groups them into a readable summary, so no lift above baseline.

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 starts with 'Search FDA medical-device recall records' – a specific verb and resource – and enumerates the searchable dimensions (firm, product, product code, K number, status, date). It clearly differentiates from sibling tools like fda_device_adverse_events and fda_device_510k_search by centering on recall records, and the additional sentence about correction/removal actions clarifies the domain.

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 that this tool searches recall records, and the caveat 'does not by itself establish patient harm' implicitly tells users not to use this for harm claims. However, it does not explicitly name alternative tools or provide when-not-to-use exclusions, so it falls short of full explicit guidance.

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