SatoshiMacro Market Data

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

Beyond the read-only/idempotent annotations, it discloses refresh cadence ('Refreshed daily'), a real history limitation ('history is month-end only'), and that history is 'computed point-in-time from that date's top-50 ranking' — exactly the kind of caveat an agent needs to avoid misreading the series.

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-loads the metric definition, then usage, then cadence caveats. The definition sentence is dense due to the nested parenthetical, but every clause (scale, exclusions, lookback, thresholds) carries meaning.

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 parameters, no output schema, and safety already covered by annotations, the description fully supplies the remaining burden: what the index means, what accompanying values are returned, how fresh the data is, and the history granularity.

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 no parameters, so there is nothing for the description to disambiguate. Baseline for a zero-parameter tool is 4.

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?

Names a specific resource (Altcoin Season Index) and gives its exact scale, computation basis, exclusion rules, and thresholds. The verb/resource pairing plus the sibling set (ETF flows, cycle indicators, market snapshot) makes the scope unmistakable.

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?

Explicitly states when to invoke it: 'Use this when the user asks whether it is altcoin season or how altcoins are performing against Bitcoin.' No alternatives or when-not-to-use cases are named, but the trigger conditions are clear.

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 (readOnly, idempotent, non-destructive, closed-world), so the bar is low. The description adds genuinely useful operational context: the upstream source (ASX Investment Products report) and the publication lag ('published a few weeks after month end, so it lags'), which matters for freshness expectations. It stops short of stating pagination or exact return shape.

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-loads the data content, then usage, then the caveat and sibling pointer. Three sentences, each carrying distinct information, with no repetition of the title or annotations.

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 carries the burden of describing return content and does so (AUM by fund, issuer, management fee, plus prior-month total). Coverage boundaries, source and lag are all disclosed, leaving nothing an agent needs before calling 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?

The tool takes zero parameters, so there is nothing to document and the baseline is 4. The description correctly implies a no-argument, fixed-scope retrieval.

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?

Names a specific resource (month-end AUM of ASX-quoted spot Bitcoin ETFs), enumerates the covered tickers (VBTC, BTXX, QBTC, IBIT), and states the unit (AUD millions) and returned breakdown (by fund with issuer and management fee). An agent can distinguish it from get_bitcoin_etf_flows without opening any 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?

Explicit when-to-use ('questions about Australian Bitcoin ETFs, their size or fees') and explicit when-not-to-use with a named alternative ('does not cover US-listed ETFs (use get_bitcoin_etf_flows)'). Routing is fully determined.

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?

Goes well beyond the annotations (which only cover read-only/idempotent/safe) by disclosing data-availability behavior: US trading days only, no weekend/holiday entries, and a one-session publication lag for the latest day. That latency and gap information materially affects how an agent should call and interpret the 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?

Front-loaded with purpose, then usage, then constraints and scope; no filler sentences. The opening sentence is dense with three comma-separated output clauses, which slightly reduces scannability but every clause carries information.

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 carries the return-value burden and does so: it names the per-fund breakdown, the 5-day/30-day sums, and the daily totals series. Data gaps (weekends/holidays) and freshness lag are also covered, so nothing needed to call it 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 coverage is 100% for the single 'days' parameter, so the schema already documents type, bounds (1-30) and default 10. The description restates the cap ('up to 30 recent daily totals') and default without adding new semantics, so the baseline of 3 applies.

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 ('Net daily flows into US spot Bitcoin ETFs in USD millions') and enumerates the exact outputs: per-fund split, 5-day/30-day sums, and up to 30 daily totals. The 'US spot' qualifier distinguishes it from the sibling get_australian_bitcoin_etfs without needing to open a 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 explicit triggering conditions ('Use this when the user asks about ETF inflows or outflows, institutional demand or a specific fund's flow') and a scope exclusion ('Flows only, not fund holdings or prices'). It does not name the sibling alternative (e.g. Australian ETFs) for non-US requests, so routing across siblings is only implied.

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 readOnly, idempotent, non-destructive, closed-world. The description adds genuinely useful behavior beyond that: indicators mix daily/monthly cadence so each reading carries its own date, and USD price is derived from AUD at the daily AUDUSD rate with a 1-2% deviation from global quotes. This data-provenance caveat is exactly the kind of context annotations cannot convey.

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?

A single well-structured paragraph, front-loaded with the indicator list before the routing guidance and the caveats. Dense but every sentence carries information; the caveat sentences are longest but they are the highest-value content.

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?

No output schema exists, so the description carries the burden of describing return values — and it does, listing the four indicators, their percentile zones, per-reading dates, and the AUD/USD price fields. For a zero-parameter read tool it is 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?

The tool takes no parameters, so the baseline is 4. There is nothing to document, and the description correctly spends no space on inputs.

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 and enumerates exactly which four indicators are returned (MVRV Z-Score, Risk Metric, 200-week MA ROC, Pi Cycle Bottom ratio). It explicitly distinguishes itself from the sibling get_cycle_model_reading, so an agent can route without opening either 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 an explicit when-to-use ('asks about a specific on-chain or valuation indicator or wants the components behind a cycle view') and names the alternative (get_cycle_model_reading) with the condition that selects it. Nothing is left to inference.

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 readOnly/idempotent/non-destructive/openWorld=false, but the description adds genuinely useful operational context: refresh cadence (twice daily, ~07:30 and 13:30 Sydney), what the date field means (last completed day), and an explicit scope caveat ('descriptive data, not a price forecast or trading signal'). That is real disclosure beyond the structured fields.

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?

Purpose is front-loaded in the first clause, and the long second sentence is dense with return-field and tier detail rather than padding. It is on the long side, but nearly every clause (cadence, date semantics, disclaimer) 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?

With no output schema, the description compensates by enumerating the return payload (zone, 7- and 30-day change, six tier scores, 30 days of history) and the zone vocabulary. Combined with the asset enum and cadence note, an agent has everything needed to call and interpret this correctly.

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% and the enum already documents BTC (default) or ETH, so the schema carries the parameter burden. The description adds meaningful model context (BTC uses 48 signals, Ethereum fewer) but no invocation-level detail beyond what the schema states; baseline 3 applies.

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 (current SMM score for BTC/ETH) and defines exactly what the score is: a 0-100 confluence score from weighted percentile-ranked signals in six named tiers. It explicitly distinguishes itself from the sibling get_market_snapshot, so an agent can route without opening either 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 concrete trigger conditions ('where Bitcoin or Ethereum sits in its market cycle', 'how the cycle score has moved recently', 'which tier is driving it') and names the alternative plus the condition that selects it ('use get_market_snapshot instead for a one-line overview'). Nothing is left to inference.

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 establish the safe-read profile (readOnlyHint, idempotentHint, openWorldHint=false), so the description is not carrying that load. It still adds real behavioral context beyond the annotations: it flags exclusivity ('the only tool that returns Fear & Greed') and describes the return shape ('each line carries its own date and source page'), which is valuable given there is no output schema.

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 payoff ('one-call overview of the whole dataset') followed by the content inventory and the routing rule. The inventory sentence is long and list-like, but every clause maps to a distinct data source, so little 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?

For a no-parameter, no-output-schema tool, the description must stand in for the return contract, and it does so by enumerating the data families returned plus the note about per-line dates and source pages. It stops short of describing the container format, but the snapshot concept is clear enough to call correctly.

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 there is no per-argument semantics to convey; the schema-coverage signal is trivially satisfied. The description correctly spends its budget on scope and return content instead of non-existent parameters.

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?

Names a specific verb+resource ('one-call overview of the whole dataset') and enumerates exactly which readings are returned (SMM scores, BTC price, Altcoin Season Index, ETF flows, Fear & Greed). It also explicitly distinguishes itself from siblings, so an agent can tell it apart from get_altcoin_season or get_cycle_indicators without opening any 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 an explicit when-to-use trigger ('broad questions like how is the crypto market looking' or several readings at once) and an explicit when-not with named alternatives ('call the specific tool instead when the user needs history, per-fund detail or tier breakdowns'). Nothing is left to inference.

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