Model a priced round

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

Annotations declare readOnlyHint=true, idempotentHint=true, so the agent already knows this is a pure computation with no side effects. The description adds valuable context beyond this: the specific conversion rules applied (MFN handling, YC post-money SAFE pool treatment implied), the scope of outputs, and that it performs full dilution math rather than a single point estimate. This additional detail about what the model computes is genuinely useful, though it doesn't discuss precision guarantees, error conditions, or performance characteristics.

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?

The description is a single, dense sentence that front-loads the core purpose and enumerates capabilities. Every clause earns its place by specifying a distinct feature. However, it is quite long and could benefit from a sentence break to separate inputs from outputs, which slightly affects readability. Still, no filler or redundancy.

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 complex financial modeling tool with 5 parameters, nested objects, and only 20% schema description coverage, the description should do more to compensate for the sparse parameter documentation. It covers the high-level purpose and outputs well, but leaves significant gaps around parameter formats, default behaviors, and edge cases (e.g., how pricePrecision interacts with computed prices, what happens if both pricePerShare and preMoneyValuation are provided). The lack of an output schema means the description appropriately describes return values, which it does, but overall completeness is only adequate given the complexity.

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 20%, meaning most parameters lack inline documentation. The description references many parameter concepts (SAFEs, notes, pool timing, fees, advisors) but doesn't explain their expected formats or constraints. For example, it mentions 'placement fees (cash and equity)' and 'advisor grants' without clarifying how these map to the nested schema fields like placementCashPercent vs placementEquityPercent, or the fromPool flag. The description adds conceptual coverage but leaves substantial gaps for a 5-parameter tool with nested objects.

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 precise verb+resource ('Full priced-round model') and enumerates the exact mechanics covered: SAFE conversion (post/pre-money, cap/discount/MFN), note conversion, new investor share issuance, option pool top-up, placement fees, advisor grants. It also names the return artifacts (before/after cap table, per-holder dilution, FD ownership, markdown). This clearly distinguishes it from siblings like safe_conversion_price (single SAFE) and compare_pool_timing (narrow comparison).

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?

The description implies when to use it (modeling a complete priced round with multiple instruments), but it does not explicitly state when NOT to use it or name the alternative siblings. An agent can infer that narrow SAFE pricing questions should go to safe_conversion_price or safe_ownership, but this routing is left implicit. Adequate but not explicit guidance.

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