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

Even with annotations indicating read-only/idempotent behavior, the description adds meaningful behavioral detail: it discloses that letter_category and violation_theme are best-effort heuristics, that status is derived from response/closeout dates, and that keyword cannot be scoped to a parsed cited-violations sub-section. It also explains the dedupe collapse behavior, going well beyond the annotation hints.

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 information-dense but every sentence serves a purpose: stating the core function, listing filter capabilities, explaining derived fields and dedupe, providing cross-tool navigation, and setting expectations about heuristic limitations. The key search behavior is front-loaded, and the structure is logical.

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 14 parameters and no output schema, the description is remarkably complete. It tells users what each returned row contains (derived status, letter_category, fei_number for one-hop navigation), explains the heuristic nature of certain fields, and explicitly notes a limitation of keyword search. This fully compensates for the absence of an output schema.

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, but the description significantly enhances parameter understanding by explaining how derived parameters (status, letter_category, violation_theme) are computed from other fields. It also clarifies the purpose of dedupe and fei_number for navigation, adding meaning not present in the schema.

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 official FDA warning letters with full-text content, using a specific verb ('Search') and resource ('warning letters'). It also distinguishes itself from sibling tools by noting it 'adds narrative context beyond fda_compliance_actions, which only contains dashboard metadata.'

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 explicitly tells users when to use keyword search versus filters ('Use keyword search for the actual letter body, or filter by...'), advises setting dedupe=true for prospecting, and contrasts with the alternative fda_compliance_actions. This gives clear usage context and exclusions.

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