Compute XIRR

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

With no annotations, the description carries the full transparency burden. It does add important conventions: outflows must be negative, inflows positive, and the current portfolio value must be included as a final positive flow dated today. Still, it does not disclose potential failure modes such as non-convergence, the need for at least one negative and one positive flow, or the exact form of the returned annualised value.

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 dense, purposeful sentences. The core concept is front-loaded, followed immediately by the operational rules an agent needs to construct valid input. There is no filler or repetition of schema details.

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 single-parameter computation tool with no output schema, the description provides sufficient input semantics and the one special cash-flow requirement. It is missing an explicit disambiguation from compute_cas_xirr and does not mention edge cases such as non-convergence, but the description is otherwise complete for an agent to produce a valid call.

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?

The schema describes only the date format and leaves 'amount' semantically empty. The description compensates by defining the amount sign convention and instructing the agent to include the portfolio value as a final positive flow. It does not discuss ordering or duplicate-date handling, but the core meaning of the single cashFlows parameter is substantially clarified.

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 states a specific computational goal ('Annualised return across irregular cash flows') and illustrates the resource with SIP instalments, lumpsums, and redemptions. This makes it clear that the tool computes XIRR for a raw dated cash-flow series rather than for a parsed CAS file, distinguishing it from the sibling compute_cas_xirr even without naming it.

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 clearly implies when the tool is relevant: whenever an agent has a dated series of irregular cash flows and needs an annualised return. However, it never explicitly contrasts this with compute_cas_xirr or other portfolio-analysis siblings, and it gives no when-not-to-use guidance such as 'do not use for already-parsed CAS data.'

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