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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds meaningful context: it specifies the record sources (FDA Orange Book, PTAB, ANDA dockets) and includes an important caveat that dates are raw records, not legal conclusions about enforceability or launch. This exceeds the annotation baseline without contradicting it.

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?

Every sentence earns its place: an attention-grabbing opening, a concise explanation of the three joined sources, a clear statement of return values, direct use cases, and a necessary legal disclaimer. It is dense but not bloated, and the most distinctive information is front-loaded.

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's complexity, the description is thorough: it names the data sources, the exact outputs, the intended use cases, and a legal caveat. The output schema exists to cover return structure, and the parameter schema fully documents the four optional parameters, so nothing critical is missing for an agent to select and call this tool correctly.

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 all four parameters are already documented in the input schema. The description does not add parameter-level semantics beyond what the schema provides, so the baseline 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 specific actions ('Joins...', 'Returns...') and clearly names the resource ('one brand drug's patent protection'). It explicitly lists the three data sources it combines, which differentiates it from single-source siblings like orange_book_competition_profile. The output is concrete: earliest unexpired unchallenged expiry, actively contested patents, and litigating generic firms.

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 explicit use cases: 'loss-of-exclusivity diligence, generic-entry timing, or 'who is attacking this drug and where''. It implies this is the comprehensive single-call alternative to manually querying three sources, but it does not explicitly name sibling tools to use instead, so it falls just 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.