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

Annotations already establish readOnly/idempotent/non-destructive, so the description needn't restate safety. It does add real behavioral context: the conversion election rule ('Each series converts to common when that pays more') and the semantics of stacked vs pari passu payout ordering. It does not mention input limits (max 10 series) or how the result is presented, which keeps it from a 5.

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?

Two sentences, front-loaded with the core purpose and with the human-facing link relegated to the end. The second sentence is dense with comma-separated enumeration, but every item earns its place by naming a supported modeling option.

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?

There is no output schema, so the description is the only place an agent could learn what comes back — yet it never says whether the result is a per-series dollar breakdown, per-share price, or totals. For a four-parameter financial model with edge cases (zero exit value, proceeds insufficient to cover preferences), that omission is a meaningful 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 100%, so every parameter including participation, preference_multiple, and seniority is already documented inline. The description's enumeration of the same concepts ('preference multiples, non-participating, participating or capped participation, and stacked or pari passu seniority') largely echoes the schema rather than adding new semantics, so the baseline 3 applies.

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 verb-free but unambiguous statement of function: an exit waterfall splitting sale proceeds between preferred series and common. It enumerates the exact model variants it handles (preference multiples, non-participating/participating/capped, stacked vs pari passu), which sharply separates it from siblings like dilution, moic, or safe_conversion.

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?

Usage is implied by the domain naming — an agent can infer this is the tool for exit/sale-proceeds allocation. However, there is no explicit statement of when to pick this over related tools (e.g., convertible notes or SAFEs on conversion) and no preconditions called out beyond the model description.

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