Spot bitcoin ETF creation/redemption flows, computed as change in shares outstanding times NAV so price moves are removed and only genuine creations/redemptions remain. This series cannot be backfilled -- the issuer publishes only a current snapshot -- so every row was banked on the day it existed. span_days above 1 marks a row that spans a gap.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | Only rows on/after this YYYY-MM-DD | |
| ticker | No | Fund ticker, e.g. IBIT |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it delivers rich behavioral detail: it explains that price moves are removed, that the series cannot be backfilled, that every row was banked on its existing day, and that span_days above 1 flags gaps. This goes well beyond a simple 'returns flows' statement.
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 and impactful. It leads with the core definition and computation, then adds necessary caveats about backfilling and gap handling. Every sentence earns its place with no filler.
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?
Given no annotations and no output schema, the description covers the essential behavioral caveats and the meaning of span_days. It could be marginally more complete by describing the full row structure or default time range, but it is sufficient for selecting and invoking the tool.
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%, with both since and ticker documented in the schema. The description adds useful context about output semantics like span_days, but it does not add meaning to the parameters themselves beyond what the schema already provides.
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—spot bitcoin ETF creation/redemption flows—and explains the precise computation (change in shares outstanding times NAV). This clearly distinguishes it from the sibling tools, which cover congressional trades and insider transactions.
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 domain is clearly ETF flow data, so the use case is evident relative to the sibling tools. However, the description does not explicitly state when to use this tool versus alternatives, nor does it mention when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool owns a distinct data domain: congressional stock trades, Bitcoin ETF flows, and insider open-market buys/sells. The two insider tools are directional counterparts with explicit cross-references, so selection ambiguity is minimal.
All tool names use lower_snake_case and follow the same [domain]_[transaction] pattern: congress_trades, etf_flows, insider_buys, insider_sells. The parallelism between insider_buys and insider_sells is particularly clear.
Four tools is a reasonable, focused size for a financial-feeds server, and each feed is distinct. The generic 'feeds' name leaves room for more feeds to be added, but the current count is not thin enough to hurt usability.
The core workflows for each advertised feed are covered: congressional trades, ETF flows, and insider buys/sells with explicit direction separation. Minor gaps exist, such as House filings being metadata-only and no feed-discovery/metadata tool, but these do not block the intended use cases.