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

Annotations already set readOnlyHint=true and openWorldHint=false, but the description adds significant behavioral context: the one-business-day publication lag, clarification that referenceIsToday is normally false, the meaning of referenceDate, and the note about Mondays. It also explains that totalUsdM is pre-summed. These details go well beyond annotations and prevent misinterpretation of stale data.

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 a single paragraph of six sentences, each carrying essential information: scope, examples, sign convention, usage hint, the publication lag caveat, and the summation note. It is efficiently front-loaded and not overly verbose, though it could be tightened into bullet points. Still very readable and purposeful.

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 no-input tool, the description fully covers what an agent needs: what it returns, how to interpret the numbers, potential staleness (with day-of-week clarification), and how the fields relate. The output schema is absent, so the description carries complete responsibility, and it does so thoroughly. No gaps remain.

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 tool has zero input parameters, so the description has nothing to add about parameter meaning beyond the schema, which is trivially complete. The baseline for zero parameters is 4, and the description appropriately emphasizes output semantics instead. No information is missing.

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 a specific verb ('Get'), a specific resource ('latest-day net ETF inflow/outflow in USD millions'), and a clear scope ('for every tracked crypto asset'), listing all assets. It also clarifies positive/negative semantics, so an agent can understand exactly what the tool returns. While it doesn't name sibling tools, the scope is so explicit that confusion is unlikely.

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 includes a clear usage context: 'Use this for a quick dashboard snapshot.' However, it does not mention alternatives (like get_asset_flows for detailed per-asset data) or exclusions when not to use it. Since it provides a clear purpose but no explicit when-not, it falls short of the highest bar but is close.

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