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

The description goes well beyond the readOnly/openWorld annotations by disclosing key behavioral traits: source='live' vs 'catalog' with as_of dating, TOP-N being a floor not an exact exposure, bond/commodity ETFs returning no holdings by design, and unknown tickers being reported in unknown_tickers. This is precisely the kind of edge-case and data-freshness context an agent needs.

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 description front-loads the primary purpose in the first sentence, then delivers conditions and caveats in compact, well-scoped sentences. Every sentence adds distinct information — freshness, top-N limitation, asset-class exclusions, and unknown-ticker behavior — with no filler or repetition.

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?

The description covers all operational behaviors an agent must know to invoke and interpret results: purpose, input semantics, freshness, precision limitations, exclusions, and error/unknown handling. The output schema exists, so return-value details are not required in the description, and nothing critical is missing.

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 already documents the tickers parameter with examples and 100% coverage, so the baseline is 3. The description adds meaning by clarifying how tickers are treated: known ones return holdings, bond/commodity ETFs return none, and unknown ones are surfaced via unknown_tickers with no holdings. This extra semantic nuance justifies a 4.

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 opens with a specific, actionable phrase — 'ETF look-through for Chapter 2 Mode 2.2 (Concentration Check)' — and clearly states that it returns top holdings with weights for overlaying direct positions. This distinct purpose separates it from sibling tools like get_prices or get_loop, which do not perform look-through exposure analysis.

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 gives clear context for when to use the tool: when performing a concentration check in Chapter 2 Mode 2.2, and when the AI needs to overlay ETF holdings with direct positions. It does not explicitly name alternatives or state when not to use the tool, but the use-case framing is strong enough to guide selection.

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