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

Annotations already declare readOnlyHint/idempotentHint and no destructive behavior, so the safety profile is covered. The description genuinely adds beyond that: data provenance ('read daily from their issuers' files'), inclusion rules ('Mergers, spin-offs and splits are no trades: left out of the sums'), and the creation-vs-rebalancing distinction in a change. The one blemish is a reference to 'beyond_growth' behavior with no corresponding schema parameter, which muddies rather than clarifies.

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 front-loaded well, opening with the use case before the mechanics. But it is one dense block paragraph, and a large share of it narrates return contents (20-close series, net additions, index entries/exits) that an output schema already carries, so several sentences do not earn their place for a single-parameter tool.

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 tool with one optional parameter, annotations, and an output schema, the description covers selection, data sources, and inclusion/exclusion rules completely. The only gap is the dangling 'beyond_growth' reference, which points at behavior the schema does not expose and could leave an agent guessing how to trigger 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 description coverage is 100%, so the baseline is 3, but the description goes further by mapping each ticker kind (ETF like QQQ, stock like NVDA, foreign line like 7203.JP, or omitted) to a distinct output shape, which adds real meaning over the schema text. The unexplained 'beyond_growth' mention slightly undercuts the precision.

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 resource (US ETF money flows) and spells out three distinct invocation modes keyed off the ticker argument, so an agent can immediately tell what it returns for no ticker, an ETF ticker, and a stock ticker. It also explicitly separates itself from find_etfs_holding_stock and get_etf_holdings_changes, which is unusually strong sibling differentiation.

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 opens with explicit trigger conditions ('Use this when the user asks how much money went into or out of US ETFs...') and closes with explicit exclusions naming the two sibling tools that cover adjacent questions. When-to-use and when-not-to-use are both stated rather than inferred.

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