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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds domain context (CRL significance and definition) but does not disclose operational behaviors such as pagination behavior, return format, or edge cases, which would exceed annotation-provided information.

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 three short sentences: the first establishes purpose and definition, the second lists filters, and the third adds regulatory significance and a related tool. It is front-loaded, succinct, and contains no redundant or 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 straightforward search tool, the description covers what the tool does, what a CRL is, how to filter, and how it relates to another FDA tool. The absence of an output schema is compensated by the tool name and definition implying the return of letters, though specific response fields are not mentioned, preventing a perfect score.

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 provides 100% coverage with descriptions for all parameters, including fuzzy match for company_name and array search for application_number. The description merely restates these filter options without adding new semantic meaning, so the baseline score of 3 is appropriate.

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 uses a specific verb 'Search' and resource 'FDA Complete Response Letters', and defines CRLs as formal refusal-to-approve decisions on drug and biologics applications. This clearly distinguishes it from sibling tools like fda_search_warning_letters and fda_search_opdp_untitled_letters by specifying a unique regulatory letter type.

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 provides clear context by explaining that CRLs are significant regulatory events indicating application deficiencies, and mentions fda_search_drugs as a related tool for approval status. However, it does not explicitly state when not to use this tool or enumerate all alternatives, so it stops short of a 5.

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