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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description goes beyond annotations by adding behavioral details: the default limit of 20 and max of 100, and the semantic quirk that `focus` functions as the sector filter since no dedicated `sector` parameter exists. This is genuinely useful context for correct invocation.

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 is compact, front-loaded with the tool's purpose, and organized as a clean Args block. Each parameter line earns its place by adding value beyond the schema, and the sector note is integrated naturally without padding.

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 simple read-only screening tool with no required parameters, the description covers all parameters, provides valid value hints, and states limits. The only minor gap is that no output schema exists and the description does not describe the return shape, but for a screener the implied result of a filtered ETF list is likely sufficient for an agent to proceed.

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?

Although schema coverage is 100%, the description adds meaning well beyond the schema. It enumerates valid assetClass values, gives representative category examples, and crucially explains how to use `focus` for sector questions, including a concrete example mapping 'tech ETFs' to InformationTechnology. This helps the agent pick correct parameter values where the schema only gives generic descriptions.

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 verb and resource: 'Filters ETFs by asset class, category, and focus.' This clearly identifies the tool as a screening/filtering operation and distinguishes it from sibling ETF tools like get_etf_analysis, get_etf_holdings, and get_etf_exposures by emphasizing screening dimensions rather than retrieving a specific data slice.

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 explicit usage guidance for one common scenario: 'Use this for a sector question' and maps 'tech ETFs' to InformationTechnology. It also states an important exclusion: 'the screener has no `sector` filter.' It doesn't name alternative sibling tools explicitly, but the when-to-use guidance is clear enough for an agent to select this tool over a generic ETF data tool.

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