etf

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

Annotations already declare readOnly/openWorld/idempotent, and the description adds substantial beyond-schema behavior: holdings default to the 25 largest, negative limit returns the smallest, non-fund tickers return no data, premium/discount is computed against the NAV's own date close and is empty for stale NAVs unless stale_nav=true, and look-through valuation reports coverage. These are exactly the edge cases an agent would otherwise mis-handle.

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 long, but the length is justified by ten distinct indicators and the text is front-loaded with the required tickers rule before the per-indicator detail. The single dense paragraph with inline colon-delimited labels is harder to scan than a bulleted breakdown would be, which is the only real cost.

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 an output schema present and 100% parameter coverage, the description's remaining burden is domain semantics, and it covers every listed indicator plus the tricky behaviors (stale NAVs, negative limits, benchmark choice, coverage reporting). An agent has everything needed to select an indicator and call it correctly.

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 3 is the floor, and the description earns more: it explains limit semantics in domain terms (limit=-10 gives the smallest holdings), tells the agent to set benchmark_ticker to the fund's index or a same-index fund with a concrete example (SPY for VOO), and clarifies yearly=true yields per-calendar-year tracking difference. The remaining parameters (period, show_columns, start_date) are left entirely to the schema.

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 the resource (ETFs and other funds) and enumerates ten concrete analyses via the indicator enum, each with a one-line definition, so an agent knows exactly what the tool yields. It does not, however, differentiate itself from sibling tools such as 'overlap' and 'liquidity', which appear to overlap with its own get_overlap/get_liquidity indicators.

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 a concrete usage constraint ("Requires tickers='VOO'", non-ETF tickers return no data) and routes sub-needs elsewhere: get_sector_weightings/get_country_weightings for sector/country, the Finance Database server for classification, and search_metrics for finding an indicator. It never states when to prefer the etf tool over the standalone 'overlap' or 'liquidity' siblings, so tool-level selection still requires inference.

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