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

With no annotations, the description carries the full burden and does so unusually well: it explains the `impulse` state machine, why `acceleration_usd_m` and boolean `accelerating` can look contradictory (reversal case), when `reversal_recovered_pct`/`reversal_basis_usd_m` are null, that `source_inconsistencies` flags only per-day sums and leaves 30d/90d intact, that closed NYSE days return net_flow_usd_m null with market_closed: true, and that seven assets have stored history only from 2026-09-21 so their 30d/90d windows are null.

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 purpose is front-loaded in the first sentence, but the body is a ~450-word dense block with nested parentheticals and run-on constructions ('which is correct and reads like a contradiction'). Nearly every clause is informative, yet the volume and depth of caveats exceed what a tool-selection description needs, hurting scanability.

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?

There is no output schema, so the description must explain the return shape — and it does: the daily series fields, cumulative vs per-day net flow, `resolution`, `series_columns` for the columns format, null semantics for closed markets, and the meaning of every derived field. Nothing an agent needs to interpret or call this correctly 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?

Schema description coverage is 100%, so baseline is 3, but the description adds interpretive value beyond the schema: it ties `format: 'columns'` to the concrete use case (long windows, much smaller payload) and reinforces the asset/history-window caveat that governs whether the 30d/90d fields are usable. It doesn't add syntax the schema lacks, so it stays short of 5.

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?

States a specific verb+resource+scope: it returns the Spot-ETF net-flow *trend* (30d/90d net flow, direction label, daily series) in USD millions, explicitly contrasting itself with a point-in-time summary that 'only gives deltas'. An agent can tell this apart from generic snapshot siblings without opening the schema.

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?

Gives clear context for when to reach for it (when direction/speed of flow matters, not a single delta; use `availability` for point-in-time work) and routes parameter choice ('For long windows pass format: cols'). It also names an exclusion ('No ZEC or NEAR ETF data'). It stops short of naming a specific alternative sibling when the point-in-time delta is what you want.

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