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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuine context by naming the computed metrics and the dividend-reinvestment convention, but omits what the response looks like and how non-USD currency figures are derived in practice, stopping short of rich behavioral disclosure.

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?

It is a single ~55-word run-on sentence that bundles purpose, periods, metrics and currency semantics together, with compressed fragments like 'compoundsim simulates' and 'the dividends' share'. The size is reasonable and the subject is front-loaded, but the lack of sentence breaks hurts scannability.

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, the description usefully enumerates the metrics returned, and all six parameters are documented in the schema. What is missing is any note on the response structure or units beyond the currency remark, so it is strong but not fully self-contained for a data-returning tool.

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 100%, so the baseline is 3, but the description earns more: it explains that '5, 10 or 20 years, all the data, or a calendar span' map to period and the period_from/period_to pair, and it clarifies the currency semantics (USD inflation adjustment versus exchange-rate share in another currency) beyond what the enums convey.

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?

It states a specific resource and computation ('annualised past returns of the assets') and enumerates the metrics returned (total return, price return, dividend share, volatility, inflation-adjusted return), which clearly separates it from the simulate_* siblings that project forward. The phrasing 'the assets compoundsim simulates' is awkward and slightly circular, but the purpose is still unambiguous.

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?

There is no explicit statement of when to use this instead of compare_portfolios or simulate_portfolio, and no prerequisites or exclusions. Use is only implied by the word 'past', leaving the agent to infer that this is the historical-lookup tool rather than a forward simulation.

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