cryptoetf

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows it's a safe read from a closed data source. The description adds valuable behavioral context: it returns a time series of net USD millions per day with sign convention (positive = inflow, negative = outflow), and clarifies that figures are asset-level totals with no per-fund breakdown, pointing to an external source for per-fund data. This goes beyond the annotations, though it doesn't mention rate limits or pagination.

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 two sentences and front-loaded with the core purpose, then adds useful details without much waste. The second sentence includes a long list of slugs for per-fund tables, which is somewhat verbose but directly useful. It could be slightly more concise, but it remains clear and structured.

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 the tool's simplicity (one required parameter, read-only, no output schema), the description provides sufficient context: it explains the return format (time series, USD millions, sign), scope (asset-level totals, no per-fund), and points to an external resource for more granular data. It lacks explicit mention of error conditions or exact response structure (e.g., array of {date, net_flow}), but that's a minor gap given the simplicity.

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 coverage is 100% (the single asset parameter is fully described with an enum in the schema). The description does not add any parameter-specific meaning beyond what the schema provides; it only restates the asset concept. Baseline 3 is appropriate when the schema does the heavy lifting and the description adds nothing new.

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 clearly states a specific verb and resource: 'Get daily net ETF flow history for a single crypto asset over the last 30 days.' It distinguishes the asset-level scope from sibling tools like get_flows_summary and get_weekly_analytics by explicitly describing its time granularity (daily, 30 days) and scope (single asset, no per-fund breakdown).

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 provides clear context for when to use this tool: for daily net ETF flow history of one asset over 30 days. It also implicitly differentiates from siblings by noting the 30-day daily granularity and asset-level totals. However, it does not explicitly state when not to use it or name alternative tools for per-fund data or longer time series.

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

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds meaningful behavioral context: the weighting scheme, the 50/69/31 reference points, and the fear/greed zone mapping. It does not discuss caching, freshness, or latency, so it falls short of a full 5.

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?

Front-loaded with the definition before the methodology and zones, and every sentence carries information an agent needs to interpret the score. It is still dense at roughly 100 words for a zero-parameter tool, so it is slightly heavier than strictly necessary.

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?

With no output schema, the description must fully explain return values, and it does: scale anchoring, component breakdown with weights, and zone thresholds. Nothing an agent needs to call and interpret this tool 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?

There are zero parameters, so the schema imposes no semantic burden and the baseline is 4. The description cannot add parameter meaning and does not attempt to.

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 and resource ('Returns the composite CEFI'), defines the exact scope (US spot crypto ETFs, all 16 tracked assets) and the 0–100 scale, so an agent can tell it apart from the flow-oriented 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?

No explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. Usage is only implied by the domain ('sentiment index' vs the raw-flow siblings), so the agent must infer the routing decision.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description needn't restate safety. It adds useful behavioral context about publication lag and lack of per-fund breakdown, but does not describe return format, pagination, or error behavior — acceptable given the explicit annotation coverage.

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 front-loads the core purpose, then explains the publication lag and alternative source in a logical flow. The long asset enumeration is necessary for clarity but makes it slightly verbose; otherwise every sentence earns its place.

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 zero-parameter, read-only summary tool with no output schema, the description serves as a compact data dictionary: it defines the sign convention, units, lag, and coverage. It could explicitly state the response shape (e.g., a map keyed by asset), but it is otherwise complete.

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?

With zero parameters, the baseline is 4. The description does not need to explain any input parameters, and it correctly focuses on output semantics (inflow/outflow sign, units, totalUsdM).

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 the exact verb and resource: 'Get the latest-day net ETF inflow/outflow (USD millions) for every tracked crypto asset,' then enumerates the assets. This unmistakably distinguishes it from siblings like get_asset_flows or get_prices.

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 clearly explains when the data applies (published one business day in arrears, referenceIsToday normally false, Monday yields Friday data) and gives the alternative URL for per-fund breakdowns. It doesn’t explicitly name when to use get_asset_flows instead, but the scope is clear enough that an agent can infer.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine behavioral context beyond them: data provenance ('sourced from major exchanges'), freshness ('refreshed frequently'), and fixed coverage of 16 named assets. The cadence is vague, but this is useful disclosure for a price-freshness-sensitive tool.

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?

Two sentences, front-loaded with what is returned before provenance. The long asset enumeration is dense but genuinely informative for coverage checking, and no sentence is wasted.

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?

With no output schema, the description must convey return values, and it does (USD spot price plus 24-hour percentage change). It also covers coverage, source, and refresh cadence. Minor residual gaps: no output shape/ordering detail and no mention of stale-data or error behavior.

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 takes zero parameters, so the baseline is 4. The description correctly implies a parameterless, whole-market snapshot ('for all 16 tracked crypto assets'), but adds no parameter detail because none exists.

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'), resource ('current spot prices'), scope ('all 16 tracked crypto assets'), units (USD) and an additional returned field (24-hour percentage change). It enumerates the tracked assets, which makes it easy to distinguish from siblings like get_asset_flows or get_cefi_index.

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?

Usage is implied by the snapshot nature of the call — an agent can infer this is the tool for current price quotes — but there is no explicit when-to-use, no alternatives named, and no exclusions relative to the four sibling analytics/flow tools. Minimum viable guidance.

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

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

Annotations already cover safety (readOnlyHint=true, openWorldHint=false), so the bar is lower, and the description still adds real behavioral detail: the exact aggregate fields returned, that weekends are excluded from the trading-day count, and that the daily series is omitted. It does not discuss caching or freshness of the 7-day window, which is a minor gap.

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?

Three tight sentences, front-loaded with purpose, then return fields, then the exclusion rule and the summary framing. Every sentence carries information an agent would otherwise have to guess.

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?

With no output schema, the description fully compensates by enumerating the returned metrics (net flow, trading days, average flow per day, positive/negative day counts) and the weekend-exclusion rule. Nothing needed to call this zero-arg tool 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?

The tool takes zero parameters, which is the baseline-4 case. The description correctly implies a fixed default of all tracked assets over a fixed 7-day window, matching the empty schema with no ambiguity.

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 and resource with scope: 'Get 7-day aggregated ETF flow analytics for all tracked assets.' The phrase 'all tracked assets' plus 'compact momentum summary without the full daily series' hints at how it differs from per-asset siblings, but no sibling is named explicitly, so differentiation is inferential rather than stated.

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?

'A compact momentum summary without the full daily series' implies when to prefer this over a daily-series call, which is useful contextual guidance. However, it never names an alternative (e.g., get_asset_flows or get_flows_summary) or states when NOT to use it, so the agent must infer routing.

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