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 real behavioral context the annotations do not: trades are executed at next-open and results are ranked rather than raw. It still omits computational cost/latency, which matters for a backtest that runs over an arbitrary period.

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 tight sentence with the operation front-loaded and the return shape trailing. No filler, no repetition of name or 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?

With an output schema present, return-value detail need not be in the description, and all eight parameters are fully documented. For a read-only computation tool this is nearly complete; only guidance on cost/period tradeoffs and sibling differentiation 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 description coverage is 100%, with defaults, enums, and ranges documented inline (top_n, sort_by, timeframe, filter_news, min_signals, holding_period). The description restates only the ranking metric, adding nothing beyond the schema, so the 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 and resource: 'Run quantitative historical backtesting of all candlestick patterns on a symbol' and the output ('top-performing patterns ranked by composite score or win rate'). Clear and specific, but it does not differentiate itself from the lookalike sibling ta_scan_symbol, which also scans patterns on a symbol.

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 never says when to choose it over ta_scan_symbol or ta_scan_watchlist, nor when a live scan is preferable to a historical backtest. No exclusions, prerequisites, or alternatives are offered.

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 real behavioral context beyond that: the feed is 'live verified' and, on failure, the tool degrades gracefully by returning an empty list with source='unavailable' rather than erroring — a failure mode an agent needs to handle.

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, zero filler: the first front-loads what the tool does and its filtering logic, the second immediately covers the degraded-return case. Nothing is repeated from the schema 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?

An output schema exists, so return-shape explanation is not required, and the description still notes the empty/source='unavailable' case. Combined with the 100% documented schema, an agent has enough to call it correctly; only usage routing against siblings (e.g. ta_get_news) and any data-source/latency caveats are absent.

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 seven parameters (days, date_from/date_to, countries, importances, max_results) are already documented in the schema itself, including defaults, bounds, and the override behavior of 'countries'. The description reinforces symbol resolution with examples but adds little beyond what the schema already declares.

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?

Specific verb ('Get') plus a precise resource ('macroeconomic calendar events') with the scoping rule spelled out: events are auto-filtered to the currencies implied by the asset symbol. The worked symbol-to-currency examples ('EURUSD=X' -> EUR, USD; 'AAPL' -> USD) make the tool's behavior unambiguous and clearly separate it from ta_get_news or the pattern/scan siblings.

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 rather than stated: an agent can infer you call this when you want macro events relevant to a symbol, and the 'countries' param is described as an override of the automatic resolution. But there is no explicit when-to-use guidance, no mention of when to prefer ta_get_news or a raw calendar, and no stated prerequisites.

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 and external-source profile is covered. The description adds no behavioral context beyond that — no news freshness window, source coverage, latency, or rate-limit behavior — and the return-field list it does give is redundant with the 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?

A single front-loaded sentence with the action, resource, return fields, and parameter inline. No filler and nothing buried.

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 a complete input schema, an output schema, and annotations covering safety, the description needs little more. The one real gap is the time window for 'recent' news, which an agent cannot derive from the structured fields.

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 symbol and limit (default 10, max 50) are fully documented in the schema. The description only repeats the symbol examples already present in the schema, adding no new semantics.

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 gives a specific verb (Fetch) and resource (recent market news headlines, publishers, timestamps) scoped to a ticker symbol. It is unambiguous against siblings like ta_scan_symbol, ta_backtest_patterns, or ta_get_economic_calendar, though it never names an alternative to differentiate 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 when-to-use guidance, no statement of prerequisites, and no mention of when a different tool would be preferable. The agent must infer the news-fetching role purely from the resource noun.

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 safety profile is covered. The description adds that the response also reports TA-Lib binary status and Python No-GIL runtime status, which is useful context about diagnostic content, but nothing about auth, limits, or failure modes — and with an output schema present, some of this may already be documented.

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 with no filler; every clause (patterns, TA-Lib status, No-GIL status) contributes distinct information about what the call returns.

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 listing tool with an output schema and full annotation coverage, the description supplies everything needed to select and invoke it. Return-value details are delegated to the output schema, which exists.

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 and the schema has no properties, so there is no parameter semantics to explain. The baseline for a parameterless tool 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 ("List") and resource ("candlestick patterns") and is clearly distinguishable from siblings like ta_scan_symbol, ta_scan_watchlist and ta_backtest_patterns, which perform operations rather than enumerate. It does not name an alternative, but the purpose 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 enumeration intent implies its use as a discovery step before scanning or backtesting, but the description never states when to call it versus the scan/backtest siblings, nor any prerequisites. Usage is inferred rather than stated.

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 conveys the output shape (patterns, confluence scores, trade setups with entry/SL/TP levels), which is behavioral context beyond the annotations, but it omits the data source, lookback clamping behavior, and any latency or rate-limit characteristics.

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 leads with the action and resource, then the computed outputs; there is no filler or repetition. The parenthetical enumerations make it slightly dense 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?

An output schema exists, so return-value detail is unnecessary, and annotations cover the read-only/open-world profile. The description is sufficient for an agent to select and call the tool, with only minor gaps around when this scan should be preferred over the watchlist or backtest siblings.

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% – every parameter (period, timeframe, compact, max_patterns, lookback_bars, min_confidence, include_brief) already carries its own description and defaults in the schema. The description adds no parameter-level meaning, so the 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?

The description names a specific verb ('Scan') and resource ('a market symbol'), and enumerates exactly what is produced: candlestick patterns, AI Confluence Scores (Trend + RSI + Volume + ATR), and trade setups with Entry/SL/TP1/TP2. It is unambiguous what the tool does, but it never contrasts itself with the sibling ta_scan_watchlist, so sibling differentiation is only implied by the singular 'a market symbol'.

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: the asset-class list ('Stocks, Crypto, Forex, Indices, Commodities') and example tickers tell the agent what inputs are in scope, but there is no explicit when-to-use guidance nor when to prefer ta_scan_watchlist or ta_backtest_patterns instead. No exclusions or prerequisites are stated.

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 the descending AI-Confluence ranking behavior and the 25-symbol cap, but the cap duplicates the schema's maxItems and nothing is said about cost/rate behavior of scanning many symbols; the schema's 'compact' note covers token usage instead.

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 names the operation, the batch constraint, and the sort order with no filler. Every clause 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 a full input schema, an output schema, and read-only annotations, the description covers the essentials an agent needs to invoke the tool. The remaining gap is usage routing versus ta_scan_symbol, which is the one thing structured fields cannot supply.

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% across all seven parameters, so the schema already carries the semantics. The description restates only the 25-symbol limit and adds no new detail on period, timeframe, min_confidence, lookback_bars, or how ranking interacts with max_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 (scan), a specific resource (multiple ticker symbols in batch), a scope cap (up to 25 symbols), and the output ordering (ranked by AI Confluence Score descending). The 'multiple ... in batch' phrasing implicitly separates it from ta_scan_symbol, but the sibling is never named, so the differentiation rests on inference.

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 only implied: the batch/watchlist framing suggests this is the tool for scanning a list of symbols at once. There is no explicit when-to-use, no when-not-to-use, and no routing to ta_scan_symbol for single-symbol scans, so an agent must infer the boundary itself.

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