finance.irr

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

Annotations only declare readOnly/idempotent/closed-world, but the description goes far beyond: it names the primary solver (Newton), the bisection bracket (-0.99 to 10) used on failure, the max_iter ceiling of 10000, the failure contract (irr=null, converged=false), and the critical unit caveat that monthly cash flows yield a monthly rather than annualized rate. These are exactly the behavioral traits an agent cannot infer from structured fields.

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?

Front-loaded with the definition, then constraints, then failure behavior, then the units caveat — a sensible order with no filler. The Newton/bisection sentence is somewhat implementation-detail heavy, but it justifies the max_iter limit and the convergence flag, so it largely earns its place.

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 4-parameter numerical solver with a defined output schema, the description covers the input domain constraints, solver robustness, failure signaling, and rate-frequency ambiguity. The only remaining gap is that 'tol' and 'guess' are never explained, which matters for an iterative root-finder where a bad guess can trigger the bisection fallback.

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 0%, so the description must carry parameter meaning; it does so for 'cashflows' (ordering, sign constraints, minimum length) and 'max_iter' (upper bound), which are the parameters most likely to cause errors. It says nothing about 'tol' or 'guess', leaving two of four parameters undocumented anywhere.

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?

States a precise verb+resource: computes IRR, defined explicitly as the periodic rate where NPV = 0, which also draws a clear conceptual line to the sibling finance.npv. The agent knows exactly what mathematical result is produced without opening the schema.

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 conditions for the inputs are stated (cashflows ≥ 2, index 0 = t=0, must contain both positive and negative values), which effectively tells the agent this tool fails on all-positive or all-negative streams. However, there is no explicit routing versus alternatives such as finance.npv, finance.cagr, or finance.bond_ytm, so sibling selection is left to inference.

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