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

Annotations already establish readOnly/idempotent/non-destructive, so the safety profile is covered; the description still adds real value by disclosing that every method returns a central value plus dispersion (sigma, percentiles, long-tail), that no defaults are applied, and that bad input yields an INVALID_ARGUMENT error envelope rather than raising. It does not contradict the annotations.

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 purpose, then usage/exclusions, then the method-to-input catalog. The method listing is long but each term carries load for a 27-parameter tool; only the repeated 'range_method' tail across every method is slightly wasteful.

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 27 params, one required discriminator, full schema coverage, and an existing output schema, the description supplies everything an agent needs: purpose, routing versus siblings, the per-method input contract, no-defaults rule, and error behavior. Return-value detail is correctly left to the 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%, which alone would cap the baseline at 3, but the description goes well beyond the per-field schema text by mapping each of the seven method enum values to the exact inputs it requires (e.g. merton_equity: firm_value, firm_volatility, debt, risk_free, maturity) and stating that exactly one method's declared inputs must be supplied. That mapping is genuinely unavailable from the flat 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?

States a specific verb+resource (value currently unprofitable companies) and enumerates the exact method families the engine covers. It explicitly distinguishes itself from siblings by naming calculate_expected_value (probability weighting of arbitrary scenarios) and calculate_dcf (single going-concern DCF), so an agent can route correctly without opening any 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?

Gives an explicit trigger ('Use this when earnings-based multiples break down') plus two named alternatives with the precise condition that selects each. Coverage of when-to-use and when-to-use-something-else is essentially complete.

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