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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds real behavior: the data is static with 'no market-data fetch', and a ticker with no proxy chain simply starts at its own inception — an edge case an agent could not infer from the schema or 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?

The core capability is front-loaded in the opening clause, and nearly every sentence carries information (return payload, use cases, alternatives, edge case). The middle sentence is a very long list of outputs that borders on run-on and could be tightened, costing it the top mark.

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?

There is no output schema, so the description carries the full burden of describing the return payload — and it does so field by field (proxy chain, extended start month, tracking grade, worst tracking error, CAGR deltas, decline counts). Combined with the edge-case and read-only notes, an agent has everything needed to call and interpret it.

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% and the single parameter is fully documented, so the baseline would be 3. The description goes further by clarifying that one ticker is accepted per call and by defining value semantics for tickers lacking a proxy chain (they start at own inception), which is meaning beyond the schema's format description.

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 names a specific verb+resource (report how far back a fund can be backtested, via its proxy chain) and enumerates exactly what it returns: proxy chain, extended start month, ETF's own first month, tracking grade, CAGR comparison, and count of S&P 500 declines added. It is immediately distinguishable from siblings like portfolio_returns and analyze_portfolio, which it names as the tools for adjacent needs.

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?

It gives explicit triggering questions ('can I backtest VXUS to 2000', 'how reliable is the pre-2011 data for BND') and an explicit timing rule ('before quoting any long-run number for a fund'). It also routes to alternatives: portfolio_returns for returns, analyze_portfolio for portfolio start-date rules.

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