market-data

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds a meaningful behavioral nuance: 'Background context, not the primary signal,' which tells the agent how to weight this information in analysis. No contradiction with 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?

The description is two sentences, front-loaded with the tool's purpose and then listing specific data elements. Every word contributes meaning, and the structure is easy to scan. No fluff or redundancy.

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 zero parameters and no output schema, the description still fully covers what the tool returns and when to use it. It lists all key data components and sets expectations for its role as background context. This is complete enough for an agent to select and invoke the 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?

The tool has zero parameters, so there is nothing to explain about params. The description adds semantic value by enumerating the data categories returned, which is more than the empty schema provides. Baseline for 0 params is 4, and the description fully compensates with content detail.

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 the tool provides crypto market context, listing specific components (BTC/ETH dominance, market cap, Fear & Greed, funding rate, stablecoin supply ratio). This differentiates it from siblings like get_macro_context and get_sentiment_data by specifying the exact crypto-focused data it returns.

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 explicitly says 'Use ONLY when analysing crypto assets (BTC, ETH, crypto ETFs)' and adds 'Background context, not the primary signal,' giving clear when-to-use and what-not-to-treat-as guidance. This effectively guides selection against sibling tools, though it doesn't name alternatives directly.

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 description adds substantial behavioral context beyond the annotations: it specifies the event scope (active events today), the output features (forward returns at multiple horizons, sample size, baseline), and a statistical caution about small samples. Annotations already establish safety (read-only, idempotent), so the description's value lies in explaining the data semantics and limitations. No contradiction exists.

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 concise yet comprehensive, using three sentences to convey the purpose, output details, and a caution. It is front-loaded with the primary purpose and avoids redundancy. Every sentence earns its place, making it efficiently structured for quick comprehension.

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 has only one parameter and no output schema, the description is exceptionally complete. It explains what events are considered, what metrics are returned (forward returns, sample size, baseline), and the interpretative caveat. An agent can fully understand the tool's behavior and result set without additional structured metadata.

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 input schema already provides 100% coverage for the single 'ticker' parameter, including an example ('SPY'). The description reinforces that the ticker is the subject of the event analysis but does not add new meaning beyond the schema. With high schema coverage, a baseline score 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 clearly states the tool's function: providing historical base rates for technical events firing on a ticker today, with concrete examples (RSI, golden/death cross, 52-week high/low). It distinguishes itself from sibling tools by focusing on forward returns and event studies rather than current indicator values, making its unique purpose 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 description implicitly conveys when to use the tool: when historical context for today's technical events is needed, or to answer 'what usually happened after this.' It does not explicitly compare to alternatives or state when not to use it, but the context is clear enough for an agent to select it appropriately. A minor gap is the lack of explicit exclusion guidance against using it for non-event historical queries.

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 read-only, idempotent, and non-destructive. The description adds value by listing the exact output fields and the either/or input requirement. It does not cover errors or return format, but the strong annotation coverage lowers the burden.

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 extremely concise, consisting of two sentences that front-load the purpose and output fields, with no redundant content. Every phrase contributes directly to understanding the tool.

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 simple read-only lookup with only two optional parameters and no output schema, the description provides enough information to invoke the tool and understand its result fields. It lacks edge-case descriptions, but those are not critical for selection and basic invocation.

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 both parameters, but the description adds essential relational semantics: the two parameters are alternatives ('Provide either...'), which is not evident from the schema. It also confirms instrument_id is a UUID and gives a concrete ticker example.

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 action ('Get') and resource ('financial instrument'), and enumerates the particular data fields returned (price, price changes, market state, 52-week range, earnings date). This distinguishes it from sibling tools such as get_price_history or get_technical_indicators.

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 implies the tool is for a current snapshot of instrument information and specifies that either an instrument_id or ticker must be provided. However, it does not explicitly name alternative tools or state when not to use this one, missing the highest bar.

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 the tool read-only, idempotent, and non-destructive. The description adds valuable behavioral context: each lens reports rising/falling versus 50-day average and 20-day change, with an overall posture of risk_on, risk_off, or mixed. This clarifies output structure beyond what annotations provide.

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 dense yet well-organized, using three sentences to convey purpose, output behavior, and parameter customization. Every clause earns its place, and the front-loaded 'first-pass read' immediately frames the tool's role.

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 adequately explains return values by describing that each lens reports trends and the overall posture. It covers the tool's functionality and focus parameter. Minor gap: it doesn't explicitly state the default behavior when focus is omitted, but it is implied as a general view.

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 schema covers the focus parameter with an enum and description, so baseline is 3. The description adds meaning by explaining that focus adds asset-class-specific lenses, but it includes 'crypto' as an option while the schema enum excludes it. This inconsistency could mislead an agent into passing an invalid value.

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 the tool's purpose: a first-pass read of market environment through price-ratio lenses, enumerating specific asset-class rotations, risk appetite indicators, defensive flows, and the dollar. This distinguishes it from sibling tools like get_macro_context or get_market_breadth by focusing on cross-asset ratios.

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 as a first-pass read, suggesting it should be used early in analysis, but it does not explicitly state when to prefer this tool over alternatives like get_macro_context or get_market_breadth. No exclusions or alternative tool references 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 declare readOnlyHint true and idempotentHint true. The description adds behavioral detail beyond annotations: it explains the methodology (clustered swing highs/lows with touch counts) and output specifics (nearest levels above/below with distance %). This is useful context without contradicting 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?

The description is two sentences long, front-loaded with the main verb and resource, then lists components and ends with a concrete use case. Every sentence adds value with no redundancy or 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?

With no output schema, the description carries the burden of explaining what is returned, and it does so: it lists the types of levels computed and states it returns nearest resistance/support with distance percentage. It could specify output structure more precisely, but the core behavior is adequately covered.

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 schema fully documents the single parameter 'ticker' with an example ('SPY'). The description merely says 'for a ticker' without adding new semantic details. With schema coverage at 100%, 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 clearly states the tool computes key price levels for a ticker and enumerates the specific components: support/resistance zones, round numbers, moving averages, and 52-week high/low. This distinguishes it from sibling tools like get_technical_indicators or get_price_history by specifying a distinct resource and output.

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 a clear use case: 'Use these for concrete trigger/target/invalidation levels.' This gives context on when to apply the tool. However, it does not explicitly mention alternatives or when not to use it, though siblings imply broader coverage.

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, idempotentHint, and destructiveHint false, covering the safety profile. The description adds the data content (sector metrics, Treasury yields, CPI, specific ratios) but does not disclose caveats such as data freshness, update frequency, or whether the figures are current or historical. This mirrors the high example where return format/pagination were missing, so 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?

The description is two sentences long, front-loads the purpose, and includes no filler or redundant wording. Every element adds 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 must convey what the tool returns. It lists the major data categories, but lacks detail on timeframes (e.g., sector performance period), units, or formatting. This is sufficient for a simple list but leaves some ambiguity for a macro context snapshot.

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 no parameters, so the schema provides complete coverage (vacuously). The description does not need to explain parameter semantics. Baseline of 4 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 states a clear action ('Get macro market context') and lists specific data types (sector P/E ratios, sector performance, US Treasury rates, CPI, inter-market ratios). This distinguishes it from siblings like get_crypto_context (crypto) and get_intermarket (intermarket focus), even if there is some overlap with get_intermarket.

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 opening phrase implies usage for macro market context, but it does not explicitly state when to choose this tool over its siblings, nor does it mention when not to use it. Given the overlap with get_intermarket for ratios, clearer guidance would be helpful.

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, destructiveHint=false, and idempotentHint=true, establishing a safe read-only operation. The description adds behavioral context by detailing the contents (percentage above MAs, RSI, trend, 52-week range), which goes beyond the annotations. It does not specify return format, but given the simplicity and read-only nature, this is adequate.

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, front-loaded with the core definition, and every word adds value. It is concise without omitting essential details, making it highly 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?

Given the tool has no parameters and no output schema, the description fully explains the tool's purpose and content. It is complete for its complexity, and the read-only annotations cover the safety profile. No significant information gaps remain.

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 has zero parameters, so the input schema fully covers the interface. The description adds no parameter-specific details, which is appropriate. Baseline of 4 for a no-parameter tool is justified.

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 identifies the tool as a measure of S&P 500 market breadth, specifying the exact computation (percentage above 50-day and 200-day MAs) and additional components (RSI, trend, 52-week range). It distinguishes itself from sibling tools like get_technical_indicators or get_relative_strength by focusing on breadth rather than raw indicators or comparative strength.

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 conveys the purpose of measuring how broad an advance or decline is, providing clear context for when one would use this tool. It does not explicitly name alternatives or state when not to use it, but the context is sufficient for a tool with no parameters and a unique niche among siblings.

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 read-only, idempotent, non-destructive. The description adds context about return content (options, instructions, channels) and clarifies it is for setup rather than analysis. No contradiction; but it could mention how the optional 'intent' parameter affects results.

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: first states purpose and key content, second gives usage boundary. No fluff, front-loaded with the most important information. Excellent efficiency.

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 informational tool with one optional parameter, the description covers what it does, the domain it serves, and when to invoke it. No output schema, but the description gives a clear sense of the return value. Complete enough for an agent to select and 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?

Schema covers 100% of the single parameter with an enum and description, so the tool description doesn't need to add much. It doesn't explicitly map its category list to enum values, but the schema's 'intent' field is self-explanatory. 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?

The description clearly states the tool's function: returning available monitoring options (price alerts, idea tracking, watchlist, digests) with setup instructions and channels. It distinguishes itself from sibling get_* tools that focus on market data or context, not ongoing monitoring.

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 use ('Call only when the user asks for ongoing monitoring or notifications') and when not to ('never needed to answer a question'). This provides clear selection criteria relative to the many sibling 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 idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context beyond annotations: data frequency is daily, and period_days has a default (365) and max (3650). No contradictions with 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?

Two sentences, front-loaded with the core function. No wasted words; every part adds value.

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 simple read-only tool with 2 parameters and no output schema, the description is complete: it states the return format (OHLCV), default/max limits, and safety is covered by annotations. Sibling tool names reduce ambiguity.

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% with both parameters fully described. The description reinforces period_days behavior but adds no new meaning beyond the schema. Baseline 3 is appropriate; it does not compensate for any coverage gap.

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 the tool's function: 'Get daily OHLCV price history for a ticker: open/high/low/close/volume.' This is a specific verb+resource scope that distinguishes it from sibling tools like sentiment or key levels.

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 clear usage hint for period_days ('Use period_days to control how far back'), but it does not explicitly state when to use this tool versus alternatives or when not to use it. The intended use is implied by the specificity of daily OHLCV data.

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 idempotentHint=true, covering the safety profile. The description adds behavioral disclosure by listing the outputs: 'current ratio, SMA(50)/SMA(200) of ratio, RSI of ratio, trend direction', which helps the agent know what to expect. No contradictions with 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?

The description is two sentences, front-loaded with the core action and return values. Every sentence contributes useful information with no redundancy or wasted words.

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?

The tool has no output schema, so the description appropriately lists the key return values and provides usage examples. It is complete for a read-only calculation tool, though it could optionally elaborate on how to interpret trend direction, but that's not essential.

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 ticker_a, ticker_b, and period_days each clearly described and exemplified. The description reinforces the A/B direction but adds little beyond the schema, so the baseline score 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 explicitly states the tool 'Calculate relative strength ratio between two tickers (A/B)', which is a specific verb and resource. It also distinguishes from sibling tools like get_intermarket or get_technical_indicators by focusing on the A/B ratio calculation and providing concrete inter-market examples.

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 provides clear usage context: 'Used for inter-market analysis' with concrete examples (GDX/GLD, HYG/LQD, XLK/SPY). However, it does not explicitly mention alternatives or when not to use this tool, so it falls short of a 5.

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 destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral context by enumerating the exact indicators returned (put/call ratios, AAII, VIX), which is beyond what annotations provide. It does not describe response format or potential quirks, but the added detail is sufficient.

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, directly states the tool's purpose, lists key data points, and adds a usage tip. No wasted words, fully front-loaded, and easy to scan.

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 low complexity (1 parameter, no nested objects, no output schema), the description adequately covers what it does and when to use it. It lists the indicators returned, which gives the agent an expectation of the output. It could mention return format or whether data is historical, but for a simple sentiment-getter, the current description is complete enough.

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 input schema has 100% coverage with a clear description of the 'type' parameter (all/put_call/vix). The tool description mentions the indicator categories but does not explicitly map them to parameter values. Since the schema already provides the semantics, the description adds only marginal value.

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 that the tool retrieves market sentiment indicators, listing specific data types (CBOE Put/Call ratios, AAII survey, VIX). This is a specific verb+resource combination that distinguishes it from sibling tools like get_market_breadth or get_macro_context.

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 provides a clear usage context: 'Useful for contrarian signals at extremes.' This tells the agent when to consider the tool, but it does not explicitly mention alternatives or exclusion criteria. Still, the context is concrete and actionable.

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 idempotentHint=true; the description adds that the tool returns short passages in the tool's own words with relevance scores, which goes beyond the schema and clarifies the output format. It does not mention other behavioral specifics like rate limits, but the bar is lowered given the strong 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?

The description is a single, well-structured sentence that efficiently combines the action, the resource, the rationale, and the return format. There is no redundant or unnecessary wording.

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?

This is a simple lookup tool with a clearly described purpose, explicit return format (short passages with relevance scores), and strong annotations covering safety and side effects. No gaps remain for effective use.

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 schema provides 100% coverage for both parameters (query and top_k), each with its own description. The tool description adds no additional parameter-level semantics beyond what the schema already communicates, so the baseline score 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?

The description uses a specific verb ('look up') plus a clear resource ('technical-analysis methodology') and distinguishes itself from sibling data-retrieval tools like get_technical_indicators by emphasizing synthesized notes and a consistent framework for grounding answers.

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 provides clear context for when to use the tool ('to ground an answer in a consistent framework'), implying its role as a qualitative methodology counterpart to raw data tools. However, it does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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 read-only, idempotent, and non-destructive behavior. The description adds valuable context by listing the specific indicators computed and noting the input (daily price history). This goes beyond the annotation baseline, though it does not disclose output format or data source specifics.

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 a single dense sentence that front-loads the action and comprehensively lists indicators without unnecessary filler. It could be slightly more structured (e.g., separated into multiple sentences) but remains efficient and 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?

For a tool with one parameter, no output schema, and annotations, the description covers the key aspects: what it calculates, for which instrument, and from what data frequency. It is complete enough for an agent to select and invoke the tool, though it omits return format details.

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% with a clear description for the only parameter (ticker). The description mentions 'for a ticker' and 'daily price history' but does not add new semantic details beyond the schema. It does not explain any format requirements or examples, so 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?

The description uses a specific verb ('Calculate') and clearly identifies the resource ('technical indicators for a ticker'). It enumerates the exact indicators (SMA, RSI, MACD, etc.), which distinguishes it from sibling tools like get_price_history or get_ta_methodology.

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 provides clear context on when to use this tool: it calculates technical indicators from daily price history for a given ticker. It does not explicitly compare to alternatives or state exclusions, but the scope is well-defined, making it obvious this is for derived indicators rather than raw price data or methodology.

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, idempotentHint=true, and destructiveHint=false, covering safety. The description adds valuable behavioral context: the response includes a source_url and never the full third-party text, which sets expectations about content length and attribution. No contradictions with 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?

The description is extremely concise—two sentences—and front-loads the core purpose immediately. Every phrase adds value: it states the resource, output components, the source_url constraint, and a usage rationale. No wasted words.

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 simple three-parameter schema, safe annotations, and presence of sibling tools, the description provides sufficient context. It explains the return structure (headline, summary, source_url) and the intended use case. A minor gap is the lack of any note about sort order or real-time vs. delayed data, but this is not critical for a 'latest news' 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 100%, with all three parameters (ticker, limit, days_back) well-described. The description adds minimal parameter-specific guidance beyond what the schema already provides, such as examples and defaults, so it meets the baseline for high coverage.

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 the tool's function: retrieving latest news for a ticker. It specifies the output (headline, short summary, mandatory source_url) and differentiates from broader news search by anchoring to a specific ticker. The phrase 'ground a market read' also clarifies its intended role.

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 provides an explicit use case: 'Use to ground a market read in recent, attributable news.' It does not name alternative tools or state when not to use it, but the ticker-specific scope and attribution requirement give clear context for appropriate usage compared to sibling tools like public_search_news.

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, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral details beyond annotations: it returns a short summary plus mandatory source_url, never full article text, and uses semantic search. This provides clear expectations for the agent without contradicting 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?

The description is a single sentence that is front-loaded with the core purpose and includes the most critical details (scope, output, limitation) with no wasted words. It is concise 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?

Given the absence of an output schema, the description appropriately covers the return format (short summary, mandatory source_url) and scope. It doesn't detail item structure or pagination, but for a search tool this is adequate. The description is complete enough for an agent to understand the tool's 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 description coverage is 100%, so the baseline is 3. The description does not add additional meaning to the parameters beyond what the schema provides; it focuses on the tool's output rather than parameter 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 clearly states the tool's function: 'Semantic news search across tracked instruments.' It also specifies the output format (short summary, mandatory source_url) and a key limitation (never full article text), which distinguishes it from sibling tools like public_instrument_news that likely provide instrument-specific news.

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 context is implied through 'across tracked instruments' and the limitation 'never full article text,' but there is no explicit guidance on when to use this tool instead of alternatives, nor any exclusion criteria. It lacks explicit when-to-use/when-not-to-use language.

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