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

Beyond the destructiveHint: false annotation, the description adds rich behavioral context: 'Read-only — nothing is written,' explains the simulation mechanics (liquidation-preference waterfall, SAFE conversion as if exit were the price round), and imposes the agent constraint 'Never hand-calculate any of these numbers.' No contradiction with 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?

Though long, every sentence earns its place: purpose, read-only note, workflow for running a ladder of valuations, reporting format, attention thresholds ($1M/$30M), and a final anti-hand-calculation warning. It is front-loaded with the core purpose in the first sentence and structured logically from behavior to workflow to reporting.

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 the tool's complexity and the presence of an output schema, the description is remarkably complete: it covers the single-valuation call semantics, the multi-scenario workflow with real data sourcing, the exact reporting shape (exit value, total distributed, per-investor payout and multiple), and edge-case guidance for below-last-round exits. It also names the specific sibling data tools needed for the workflow, making it fully actionable.

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 only 50% and exitValuation has no description beyond a regex pattern. The description compensates by clarifying exitValuation means a single hypothetical exit valuation ('ONE hypothetical exit valuation', 'call this once per valuation'). companyId remains a generic UUID wrapper, but the tool's overall purpose makes its role clear.

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: 'Computes what every stakeholder takes home at ONE hypothetical exit valuation, running the liquidation-preference waterfall and converting SAFEs as if the exit were the price round.' This clearly distinguishes it from sibling cap_table tools like preview_close_cap_table_round or get_cap_table_summary by emphasizing hypothetical simulation.

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?

Provides explicit contextual guidance: when the user asks for a simulation without a number, read the company's real valuations first via GetListCapTableRounds and GetListCapTableSecurities, call the tool once per valuation, and include down-round and upside scenarios. However, it does not explicitly state when NOT to use this tool or name alternative tools for the same task, so it misses the full 'when-not/alternatives' bar for a 5.

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