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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and non-open-world, so the safety profile is covered. The description still adds genuinely useful behavior beyond them: pure arithmetic with no I/O or external calls, 2-decimal rounding, no auth or rate limits, and error-not-value behavior on unknown method or missing required parameter. These are helpful but partly restate the closed-world safety model the annotations already imply.

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-loaded with purpose, then model selection, then per-method parameters, then units and return shape. Mostly efficient, but the hardware exclusion is stated twice ('for hardware or deep tech use valuation_hardware' and 'Not for hardware or deep tech — for that use valuation_hardware'), which is redundant.

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 9-parameter, method-dispatch calculator with an output schema, the description covers model selection, required vs method-dependent parameters, units/domain constraints (fractions, [0,1] summing probabilities), and error behavior. Nothing an agent needs to invoke it correctly is missing.

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% and the enum already spells out each formula, so the schema does the heavy lifting. The description adds real value by mapping which parameters each method consumes (peak_sales -> patient_population/penetration/price; decision_tree -> probabilities/terminal_value; pipeline -> drugs/discount_rate), but does not add syntax the schema lacks. Baseline 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?

States a specific verb+resource ('Risk-adjusted biotech valuation') and immediately names the three selectable models (peak sales, decision tree, rNPV) it computes. It explicitly distinguishes itself from the sibling valuation_hardware by domain, so an agent can route without opening either schema.

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?

Explicit when-to-use ('pharma/drug pipelines') and when-not ('not for hardware or deep tech'), naming the alternative tool valuation_hardware. It also states the selection rule ('Method selects the model') and that only method is required.

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