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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful context by stating the tool accepts many instrument classes (stocks, ETFs, indices, FX, futures, crypto) and by listing the computed metrics, but says nothing about data latency, rate limits, or failure behavior for invalid symbols.

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 front-loaded sentence that states purpose first, then the output metrics; nothing is wasted. The long parenthetical of symbol examples makes it slightly dense but still readable.

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 list the returned metrics (volume, relative volume, CMF, net flow, score). Combined with annotations covering the safety profile and a single fully documented parameter, this is close to complete, though it does not explain how to interpret CMF or the score.

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% and there is only one parameter, so the baseline is 3. The description does extend the symbol examples beyond the schema's list (^GSPC, EURUSD=X, GC=F), confirming breadth of accepted formats, but adds no syntax or constraint details 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?

Names a specific verb (analyze) and a specific resource (money flow of a Yahoo Finance symbol), and enumerates the metrics returned (USD volume, relative volume, CMF, net flow, score). It does not, however, contrast itself with siblings such as get_liquidity_overview, get_capital_flows or compare_flows, so an agent cannot tell it apart from those 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?

The description implies usage ('any Yahoo Finance symbol') but gives no explicit when-to-use, when-not-to-use, or alternatives. With a large sibling set of flow/liquidity tools, the absence of any routing guidance is a real gap.

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?

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that the tool ranks or orders the results, but it does not disclose the ranking criteria, return format, or any limitations beyond the schema's min/max item constraints.

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 definition is a single, efficient sentence with the comparison action front-loaded and an example included. It avoids repetition or filler, though it could be slightly more explicit about ranking behavior without becoming verbose.

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 one-parameter, read-only comparison tool with no output schema, the description is minimally adequate: it says what is compared and that results are ordered. However, it omits what 'flujo de liquidez' means in this context or what the ordered output contains, leaving the agent to infer the return semantics.

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%, and the single parameter is already documented as a Yahoo Finance symbol list. The description adds a concrete example list, but does not add syntax or format details 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 states a specific verb and resource: 'Compara el flujo de liquidez entre varios símbolos ... y los ordena.' It also clarifies the multi-symbol scope, which distinguishes it from single-symbol or overview siblings, but it does not explicitly name an alternative tool.

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?

There is no explicit guidance on when to use this tool versus alternatives such as get_liquidity_overview or get_capital_flows. The multi-symbol comparison scope implies a use case, but no when-not conditions or routing advice are provided.

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 readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds the meaningful output-ordering behavior ('Ordenado de mayor entrada a mayor salida'), which is genuinely useful and not derivable from the schema or annotations.

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 dense sentence, front-loaded with the core purpose and then the grouping semantics. Every clause earns its place; nothing is padded, though it is somewhat list-heavy.

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, and the description fills that gap by explaining the sort order of the returned ranking. For a single-parameter read tool whose annotations carry the safety profile, this is essentially complete; only the alternative-tool routing 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?

With 100% schema coverage the baseline is 3, but the description goes further by decoding each enum value: 'asset' = clases de activo, 'region' = países, 'sector' = sectores EE.UU., 'macro' = índices y divisas. This disambiguates the enums beyond the bare schema list.

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: it produces a 'ranking de flujo de liquidez' scoped 'dentro de un grupo'. The grouping concept is clear and unique, though the description never names or contrasts the obvious siblings (compare_flows, get_liquidity_overview, get_crypto_liquidity).

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 'Ranking de flujo de liquidez dentro de un grupo' — the agent can infer this returns a ranked list per grouping. However, there is no explicit when-to-use, no exclusions, and no routing to alternatives like compare_flows or get_flow_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 readOnlyHint=true and openWorldHint=true, so the safety profile and external-dependency nature are covered structurally. The description only reinforces that it pulls from third-party providers; it discloses nothing about data freshness, caching, rate limits, or failure behavior, so it adds little beyond the annotations.

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 compact sentence that front-loads the primary metric set and names each data provider. No filler, though it reads as a raw content list rather than a directed instruction.

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 conveying return values, and listing the metric families partially does so. However, it gives no sense of response structure, time window, or granularity, leaving the agent to guess at the shape of the data.

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 parameter semantics to document; the baseline for a parameterless tool is 4. Nothing in the description misrepresents the (empty) input surface.

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 enumerates the concrete data the tool surfaces — total market cap, volume, dominance (CoinGecko), stablecoin supply and its variation (DefiLlama), and the fear & greed index (alternative.me) — so an agent can tell what resource it returns. It is clear but does not differentiate itself from siblings such as get_liquidity_overview or get_macro_liquidity_history.

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?

There is no statement of when to use this tool, when to prefer an alternative, or what prerequisites exist. With 13 sibling tools covering overlapping liquidity/flow concepts, the absence of any routing guidance is a real gap.

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=true, so safety is covered. The description adds genuine context beyond that: the exact data source (FRED), the units (billions), and the composition of the metric. It does not mention update frequency, data lag, or rate limits, so this is solid but not rich.

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 dense sentence that front-loads the formula and then adds horizon and source. Every clause carries information (formula, units, windows, source) with no filler. Slightly dense but efficient.

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 one-parameter read-only tool with no output schema, the description is nearly self-sufficient: it explains the computation, units, horizons, and source. The remaining gap is sibling differentiation against other liquidity tools, which leaves some ambiguity despite the otherwise complete spec.

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 single 'weeks' parameter is documented in the schema itself. The description mentions 4/13/52-week variations and weekly history, which loosely contextualizes the history window, but adds no syntax or constraint detail beyond the schema. Baseline 3 for a well-covered single-parameter tool.

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 precise verb+resource: it computes net Fed liquidity via an explicit formula (WALCL − TGA − RRP) in billions from FRED. This is far more specific than the name alone. However, it does not distinguish itself from overlapping siblings such as get_liquidity_overview or get_macro_liquidity_history, which likely cover similar ground.

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?

There is no when-to-use, when-not-to-use, or alternative guidance. Given the crowded sibling set (get_liquidity_overview, get_macro_liquidity_history, get_crypto_liquidity), an agent has no signal about which liquidity tool to pick. Usage is only implied by the formula content.

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=true, so the safety profile is covered. The description adds useful context beyond that: the historical depth available (monthly since 1993 vs weekly 10 years) and that accumulated flow is included — meaningful behavioral/horizon disclosure. It stops short of stating auth needs, rate limits, or empty-range behavior.

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 but efficient sentences that front-load scope and period coverage, then enumerate the returned fields. No filler, though the enumeration of per-period metrics borders on output documentation that could be trimmed.

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 correctly compensates by describing the per-period return fields (return %, volume USD, net flow, intensity) and the accumulated-flow aggregate. Combined with the temporal coverage note and readOnly/openWorld annotations, an agent has enough to call it correctly; only missing details are error/empty 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?

Schema coverage is 75%, so most parameters are already documented. The description mirrors the 'group' enum values and explains that 'symbols' scopes to members of that group, which adds a little meaning, but says nothing extra about 'periods' or 'resolution' beyond what the schema already provides. Baseline 3 is appropriate.

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 (money-flow history) and specifies the two axes of retrieval: group-level ('asset','region','sector','crypto') versus explicit symbols. It also states the temporal scope (monthly since 1993, weekly 10 years). However, it does not explicitly differentiate itself from ambiguous siblings like get_capital_flows or get_rotation_history, so an agent could still hesitate between them.

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 description of what the tool returns over time, but there is no explicit when-to-use/when-not-to-use guidance and no sibling is named as an alternative. The agent must infer that this is the historical-series counterpart to overview tools.

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=true, so the safety profile is covered by structured data. The description adds that the payload is a multi-domain composite including a Spanish-language narrative, which is useful output-shape context, but says nothing about freshness, caching, or aggregation lag.

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 front-loaded sentence opens with 'Resumen completo' and then enumerates contents efficiently with no filler. The list is dense but each item earns its place by telling the agent what data domains are covered.

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 the return shape, and it does so by listing the covered domains plus the narrative summary. What is missing is a note on how this aggregator relates to the granular sibling tools and any indication of data currency.

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 schema imposes no semantic burden and the baseline of 4 applies. There is nothing for the description to clarify or compensate for here.

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 the resource precisely and enumerates its components (market regime, inflows/outflows, Fed liquidity, stablecoins, crypto, narrative summary), so an agent knows exactly what the call returns. It does not, however, differentiate this composite overview from focused siblings such as get_fed_liquidity or get_crypto_liquidity.

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?

There is no when-to-use guidance, no indication that this is the broad 'start here' aggregator versus the narrower sibling tools, and no exclusions. The reasoning is left entirely to inference from the content list.

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=true, so the safety profile is covered and this is clearly a safe read. The description adds useful context by disclosing the historical span and sampling frequency of each series (weekly from 2002, monthly from 1959, etc.), which annotations cannot convey, but it says nothing about the return shape, pagination, or dataset size.

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 dense sentence, though it front-loads the core concept ('Series largas de liquidez') before enumerating datasets, which is the right order. It is long but every clause maps to a returned series, so there is little waste.

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 rightly carries the informational burden, and it does so by listing all the datasets and their historical coverage. The main omission is that it never clarifies how the multiple series are packaged in the response, but the dataset inventory is thorough enough that an agent can call it 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 parameters ('step' with its four-value enum and frequency semantics, and 'since' with its YYYY/YYYY-MM/YYYY-MM-DD pattern) are already fully documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline of 3 is appropriate.

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, 'series largas de liquidez', and enumerates exactly which datasets are returned (Fed net liquidity, Fed balance, M2, stablecoins, crypto fear & greed, VIX, risk-on/off flow regime) with their start dates. It does not, however, differentiate itself from near siblings like get_liquidity_overview, get_fed_liquidity, or get_crypto_liquidity, leaving the agent to infer the distinction from dataset coverage alone.

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?

There is no explicit statement of when to use this tool versus alternatives. With siblings such as get_liquidity_overview, get_fed_liquidity, get_crypto_liquidity and get_flow_history, some phrasing like 'use this for long historical series; use overview for current snapshot' was needed but is absent.

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=true, so the safety profile is covered. The description usefully discloses the analytical methodology (a composite of flows, VIX, credit spread proxy, copper/gold), which helps an agent interpret the result, but it says nothing about update frequency, data freshness, or confidence/caveats.

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 front-loaded sentence: the purpose leads, then the composite inputs follow. No filler, though the trailing input list is dense and slightly run-on.

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 and no parameters, the description carries the burden of return semantics, yet it never states what is actually returned (a regime label, a score, a direction?). It also omits usage context relative to sibling analysis tools, so an agent can tell what it computes but not exactly what it gets back or when to prefer 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 the baseline is 4. The description correctly implies a parameterless, whole-market call with no filtering options to explain.

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 analytical verb ('Determina') and a clear target concept (risk-on/risk-off regime), then enumerates the exact inputs it composites (flows, VIX, HYG vs IEF, copper/gold). This distinguishes it in substance from siblings like get_liquidity_overview or get_macro_liquidity_history, though it never names those siblings explicitly.

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?

There is no statement of when to call this tool versus alternatives such as get_liquidity_overview, get_macro_liquidity_history, or get_capital_flows. Usage is only inferable from the concept of a risk regime; no context, prerequisites, or exclusions are given.

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 declare readOnlyHint=true and openWorldHint=true, covering safety and external-data scope. The description adds the analytic framing (flow intensity ranking per period) but says nothing about data sources, latency, or edge cases. With annotations covering the safety profile, a 3 is appropriate.

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, no waste. The first sentence front-loads the output definition; the second gives purpose. Efficient and well-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?

A read-only analytic tool with four parameters and no output schema. The description explains the output concept but leaves parameter meanings and default behavior undocumented, and doesn't clarify return shape. Adequate minimum but with clear gaps given the 0% schema coverage.

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 0% – none of the four parameters (top, group, periods, resolution) have schema descriptions. The description mentions 'grupo' and 'periodo' conceptually but doesn't explain defaults (top=3, periods=12, resolution=monthly), enum values, or max bounds. It fails to compensate for the complete lack of schema 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?

States a specific analytical output: per period, which instruments in a group gained or lost money by flow intensity. Clear verb-resource-analytic intent, though it doesn't distinguish itself from siblings like get_flow_history or get_capital_flows.

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?

Implies usage ('Sirve para ver cómo ha rotado la liquidez...') but gives no explicit when-to-use vs alternatives. The agent must infer that this is for rotation across group dimensions over time, not for point-in-time flows. No exclusions or alternative routing provided.

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=true, so the safety profile is covered. The description usefully adds the data source scope (scans all US stocks above the cap threshold) and the computation methodology, but omits cost/latency caveats despite describing an intraday full-market scan.

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 with no filler, front-loading the scan scope before the computed metrics. Efficient and appropriately sized for the tool's complexity.

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, and the description does enumerate the returned per-sector metrics (% al alza, valor negociado, flujo neto), which is helpful. However, it omits data freshness, timeframe granularity, and the role of the one parameter, leaving modest gaps for a market-scan 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 coverage is 0% for the single min_market_cap parameter. The description references the threshold ('capitalización > 10.000 M'), which maps to the parameter's default, adding partial meaning, but it never indicates the threshold is adjustable or how it affects results.

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 (recorre/calcula) and resource (sector breadth: % al alza, valor negociado, flujo neto intradía) with a clear scope (all US stocks > 10.000M cap). The 'medida bottom-up independiente de los ETFs' phrase implicitly differentiates it from ETF-based sector measures, but no sibling is named explicitly.

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 explains what the tool computes but gives no when-to-use guidance and no alternatives. With siblings like get_capital_flows, get_rotation_history, and tradingview_unusual_volume, an agent gets no signal for choosing this over them.

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=true, so safety and external-dependency behavior are covered structurally. The description adds that multiple symbol namespaces are accepted, which is real context, but says nothing about rate limits, batching behavior for up to 50 symbols, or result freshness.

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 that front-load what is returned before listing accepted symbol formats. Every clause carries information, though the parenthetical metric list is slightly crammed.

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 values, and it does so by naming the metrics (technical rating scale, RSI, relative volume, traded value, performance). Only minor gaps remain around ordering, limits, and failure modes for invalid symbols.

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 'symbols' array, so the baseline is 3. The description goes beyond the schema by enumerating accepted symbol conventions (US tickers, Yahoo forms like BTC-USD/^VIX/EURUSD=X, and exchange-prefixed forms like BMV:WALMEX/BINANCE:SOLUSDT), which materially reduces invocation errors.

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: TradingView technical rating with RSI, relative 10d volume, traded value and weekly/monthly performance. It clearly distinguishes itself from tradingview_unusual_volume and tradingview_sector_breadth by describing a per-symbol technical snapshot, though it does not name those siblings explicitly.

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 (fetch technical indicators for one or more symbols) but there is no explicit when-to-use/when-not, no statement of prerequisites, and no routing to alternatives. Adequate but leaves the agent to infer context.

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=true, so the safety profile is covered. The description adds that results are liquidity-filtered and represent fresh capital entering, which is useful framing, but it omits return shape, ranking logic, or any latency/rate considerations. Adequate, not rich.

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 sentence and the market list follows as supporting scope. Two sentences with no filler, though the long market list is partially redundant with the enum and slightly inflates the length.

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 read-only screener with no output schema, the description conveys what is screened, the markets covered, and the inflow-oriented rationale. An agent has enough to invoke it correctly; only the return structure is left unspecified, which is acceptable given annotations cover safety.

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 67%, a mid-range baseline. The description's market enumeration largely duplicates the schema enum rather than adding format or constraint meaning, and 'limit' carries no description anywhere. The local-currency nuance for min_value_traded lives in the schema, not the description.

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 intent: a TradingView screener surfacing assets with the highest relative volume and sufficient liquidity. An agent can distinguish it from siblings like tradingview_technicals or tradingview_sector_breadth by the 'relative volume / new money entering' framing. No explicit sibling callout, but the resource is unambiguous.

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 phrase 'dónde está entrando dinero nuevo' implies the use case (spotting inflow-driven momentum), so usage is suggested rather than stated. There is no explicit when-to-use, when-not-to-use, or alternative tool naming against the many flow/liquidity siblings.

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