fda_tobacco_problems

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description's 'Search' framing aligns with the safety profile. The description adds useful context about dataset size and content but does not disclose operational details such as rate limits, response shape, or behavior on invalid queries. There is no contradiction with annotations.

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, well-structured, and front-loaded with the core purpose, followed by actionable examples and count fields. Every section earns its place, and no filler or redundant restatement of the tool name appears.

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 two-parameter search tool, the description covers the domain, query syntax examples, limits, and useful fields, which is sufficient for most invocation scenarios. It falls slightly short because the count-field line implies aggregation capability that is not represented by any parameter in the schema, leaving the agent without guidance on how to actually use those fields.

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?

The input schema already documents both parameters at 100% coverage, so the baseline is 3. The description adds value by providing concrete field-specific query examples ('date_submitted', 'nonuser_affected') and mentioning count fields like 'tobacco_products.exact' and 'reported_health_problems.exact', which help an agent construct more meaningful searches.

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 ('Search') and resource ('tobacco product problem reports'), and adds concrete characteristics: ~1.3K reports, damages/defects/health effects, and e-cigarette dominance. It is clearly differentiated from sibling FDA tools like fda_drug_events and fda_device_events by focusing on tobacco-specific reports.

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 domain and examples make it evident when to use this tool: when searching tobacco product problem reports, including date-range and non-user-affected filters. It does not explicitly state when NOT to use it or name alternatives, but the wording is specific enough that an agent would not confuse it with FDA drug, device, food, or animal event tools.

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