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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered; the description adds genuinely non-obvious computation semantics — interest accrues on each opening balance and tax is computed on EBITDA less depreciation and interest. That is real behavioral disclosure beyond structured fields, though it does not say what happens on infeasible inputs (e.g., debt exceeding sources) or how the sensitivity grid is anchored.

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?

Three sentences, front-loaded with the core identity and then the output list, with no filler. The middle sentence is a dense comma-separated enumeration but each clause carries distinct information about the cash flow waterfall, so little is wasted.

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?

With no output schema and a deeply nested 10-parameter input, the description does well to enumerate return values (MOIC, IRR, IRR grid), but leaves gaps: currency scaling assumptions are only in the schema, tranche ordering/priority for sweeps is unstated, and there is no mention of what a partial or failed model returns. Adequate but not fully self-sufficient.

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 description coverage is only 40% across 10 parameters including a nested debt array, so the description must compensate and only partially does. It clarifies the tax/interest mechanics and implies the sensitivity grid axes ('entry by exit multiple'), but says nothing about the three-way alternative for deal size (entry_ebitda × entry_multiple vs entry_enterprise_value), the debt amount vs ebitda_multiple alternative, or how 'sweep' ordering interacts across up to six tranches.

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 opens with a specific verb and resource ('An LBO') and enumerates the concrete outputs produced: sources and uses, per-tranche interest/amortization/cash sweep, exit value and equity, MOIC, IRR, and an IRR sensitivity grid. This is unmistakably a buyout model builder and easily separable from siblings such as valuation_dcf, valuation_wacc, or valuation_football_field.

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?

It implies when the tool applies (when you want a debt-financed buyout modeled) but never states when to prefer it over valuation_dcf or valuation_football_field, nor any prerequisites such as needing entry EBITDA or an entry multiple. The trailing 'Free.' hints at a pricing/cost constraint but is not usage guidance.

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