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

Goes well beyond the readOnly/idempotent/openWorld annotations: discloses the 10-K + FDA join, the BPCIA special-case handling of undated biologics (returned separately as exposed_undated_bpcia, never assigned a year), and the caveat that expiry is pre-litigation/pre-extension. This is exactly the kind of domain behavior an agent could not infer from structured fields.

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?

Front-loads the core purpose and keeps each sentence load-bearing (join logic, edge case, caveats). It is dense and long, but almost nothing is filler; the length tracks a genuinely complex tool.

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 multi-source, no-output-schema tool the description carries much of the return-shape burden, naming exposed_undated_bpcia and protected_beyond_horizon and explaining revenue semantics. A little more on the overall response shape (ranking, totals) would close the remaining gap.

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 already 100%, so the baseline is 3. The description adds real meaning by explaining the drug-vs-company selection, that a drug's marketer resolves to a filer whose portfolio is screened, and that horizon-bounded expirations land in protected_beyond_horizon.

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?

Opens with a specific framing ("The patent cliff, in dollars") and states exactly what it computes: which products lose exclusivity soonest and how much reported revenue each carries. This is clearly distinguishable from siblings like pharma_product_sales (raw sales) and pharma_pipeline_catalysts (events).

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?

Gives explicit query modes: whole portfolio by ticker/company, or a single drug to place one product. It also states scope conditions (revenue is last reported period, not forecast; expiry is the earliest FDA date before litigation/extensions). It stops short of naming a sibling to use instead when you just want plain sales figures.

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