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

The BEHAVIOUR section adds context beyond annotations: 'pure deterministic calculation — no side effects, no network or storage access, no randomness; idempotent and non-destructive' plus the solving method ('Newton-Raphson with bisection fallback') and cash-flow schedule shape. Since annotations already declare readOnlyHint, idempotentHint, and destructiveHint, the description's additional algorithmic detail earns a 4 rather than a 5. 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, the description is modular with scannable labels — WHEN TO USE, WHEN NOT TO USE, BEHAVIOUR, RETURNS, PARAMETERS — and the core purpose is front-loaded in the first sentence. Every sentence carries information proportional to the tool's complexity (three outputs, sensitivity grid, algorithmic disclosure).

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 present, the RETURNS section fully documents the JSON shape: 'concept, definition, formula, calculation (irr as a percentage string, moic as a multiple, cash_flows array), interpretation, and sensitivity (byMultiple, byHoldPeriod)'. Combined with 100% parameter coverage, named sibling alternatives, and behavioral disclosure, nothing an agent needs to invoke this tool correctly is missing.

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 100%, so the baseline is 3; each parameter already carries a schema description covering positivity, currency units, integer restriction, and the currency enum with 'display only — no conversion'. The PARAMETERS section in the description largely restates the schema rather than adding new meaning, so it does not push above baseline.

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 opening sentence names a specific verb and resource — 'Calculate the Internal Rate of Return (IRR), MOIC and an IRR sensitivity table' — and precisely scopes it to 'a single lump-sum equity investment that returns one exit value after a whole-year hold period.' This immediately distinguishes it from siblings like calculate_npv, calculate_moic, and irr_sensitivity.

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 WHEN TO USE section states the exact trigger condition ('an upfront investment amount, a single exit value and a hold period in whole years'), and WHEN NOT TO USE routes to named alternatives ('use calculate_npv or calculate_moic on the full cash-flow array', 'use irr_sensitivity'). Tool selection is fully explicit with no inference required.

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