Crypto prices and ZEC ETF flows

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

Annotations already declare this is read-only, idempotent, non-destructive, and not open-world. The description adds meaningful operational context beyond annotations: data source is CoinGecko, prices are at most about 60 seconds old, and only top-100 coins are covered.

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 front-loaded with the resource and return fields, then immediately explains the two calling modes. Every sentence contributes useful information, and there is 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?

Although there is no output schema, the description enumerates the returned fields and data freshness. With annotations covering safety and the schema covering parameters, an agent has everything needed to invoke this tool 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 description coverage is 100%, so both `limit` and `symbols` are already documented in the schema. The description reinforces that symbols accept tickers, CoinGecko ids, or names, and that omission returns the top N, but adds little beyond the structured parameter documentation.

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 and resource: live USD prices for the top 100 cryptocurrencies by market cap, including the exact fields returned. Sibling tools are about ZEC ETF history and signals, so this tool is clearly distinguishable as crypto spot pricing rather than ETF data.

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 explicitly explains when to pass `symbols` for specific coins versus omitting them for the top N by market cap. It also states the boundary condition that coins outside the top 100 are not available, which prevents incorrect calls.

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), and the description adds useful context beyond them: chronological ordering (oldest day first), the earliest available date, and the informational-only disclaimer. It omits pagination/truncation behavior for the 365-day ceiling, 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?

Front-loaded with the core statement, then a field inventory and two short qualifying sentences; no wasted framing. The middle field list is dense (AUM, premium to NAV, streak) but each item tells the agent what it can retrieve, which is justified when no output schema exists.

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 returns, and it largely does by enumerating the per-day fields, ordering, and history start date. It leaves the relationship to get_zec_etf_signal unexplained and doesn't describe behavior at the start-of-history boundary (e.g. fewer than `days` results).

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 all three parameters are already documented in the schema. The description restates the two optional flags ('adds each day's component scores and rationale') without adding format or performance nuance, and says nothing about the `days` window 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 resource and shape: 'Daily history of the ZEC ETF flows indicator, oldest day first', then enumerates the returned fields. The word 'history' implicitly separates it from get_zec_etf_signal (current signal), but no sibling is named explicitly, so the differentiation is inferred 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?

The description gives a hard boundary ('History starts on 2026-09-07') and explains what the optional flags add, which helps an agent decide how to call it. It never says when to prefer this over get_zec_etf_signal or get_crypto_prices, so routing guidance is only implied by the word 'history'.

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, so credit here comes from the added context: the recompute cadence (once daily after US close), the precise staleness condition (ETF data more than two business days old), and the notable constraint that the LLM rationale may only downgrade the computed signal, never upgrade it. That last detail is non-obvious and materially affects how an agent should trust the output.

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 dense sentences, both front-loaded: the first establishes what the signal is and what feeds it, the second enumerates return contents and operational caveats before closing with the disclaimer. No filler and no repetition of the name/title.

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 carries the burden of describing returns, and it does: signal, total score, per-component score and reason, raw inputs, rationale, tracked funds, and recent filings. Combined with the cadence and staleness rule, an agent has everything needed to call it and interpret the result.

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 the description could add at the parameter level; the baseline for a 0-param tool applies. Nothing in the description misleads about 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?

Names a concrete artifact (the current ZEC ETF flows indicator) and states exactly what it produces: a daily BUY/HOLD/SELL signal from a named set of inputs. The word 'current' plus the 'daily' recompute cadence implicitly separates this snapshot from the historical sibling get_zec_etf_history, and no other sibling could be confused with it.

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 reader can infer this is a once-a-day snapshot rather than a query interface, and 'Informational only, not investment advice' sets a boundary. But it never says when to call this versus get_zec_etf_history, nor does it state that there are no parameters or filters — the selection guidance is implied rather than stated.

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