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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description need not reiterate safety. It adds value by disclosing that it fetches daily and intraday data, and that it returns an error string for missing data or unknown methods. This goes 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?

The description is compact and front-loaded with the core purpose. It uses bullet-style Args and Returns sections without unnecessary words. Every sentence contributes to understanding.

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 complexity (one parameter, single operation), the description covers purpose, data fetching, dispatch, return format, and error conditions. Combined with thorough schema and annotations, it is fully sufficient for an agent to invoke 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 description includes an Args section summarizing the three parameters, which mirrors the schema descriptions. With schema descriptions already present for all properties, the description adds minimal extra meaning (e.g., noting defaults). The context signal 'Schema description coverage: 0%' is contradictory to the actual schema; based on actual content, the description does not significantly improve understanding beyond the schema.

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 begins with a specific verb+resource: 'Run a registered method on a ticker to produce a trade setup.' It clearly distinguishes from siblings like quant_describe_method (which describes methods) and quant_backtest_method (which backtests). The tool's focus on a single ticker and registered method 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 description implies usage for generating a trade setup for a specific ticker and mentions feeding the result to quant_score_decision, suggesting a pipeline. However, it does not explicitly state when not to use this tool versus alternatives like quant_detect_regime or quant_compute_indicators, so no 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 already provide readOnlyHint, idempotentHint, etc., so the description adds value by detailing method-specific behaviors (e.g., xs_momentum ranks by 12-1 momentum, pairs returns spread statistics). This is sufficient and consistent 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 well-structured with a clear purpose statement, method examples, and an Args/Returns section. No unnecessary repetition, and it is 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?

Given annotations and output schema existence, the description covers all key aspects: method variants, parameter constraints, return structure, error handling, and linking to sibling tool quant_score_decision. It is complete for an AI agent to 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 input schema already provides descriptions for all parameters (100% coverage), so the description's summary of args adds marginal value. However, it enriches the parameter context with behavioral details like 'xs_momentum ranks by 12-1 momentum' and 'pairs returns beta, ADF p-value, z-score', enhancing semantic understanding.

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 it runs universe-based methods (ranking or pairs) across multiple tickers, with specific examples (xs_momentum, pairs_cointegration) that differentiate it from sibling tools like quant_screen_universe or quant_backtest_method.

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 ticker count requirements for each method and error conditions, giving context on when to use. However, it does not explicitly exclude alternatives or clarify when to prefer this tool over siblings, missing an opportunity for clearer guidance.

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 indicate readOnlyHint=true and idempotentHint=true. The description adds significant behavioral context: no separate backtest implementation, costs applied one-way, and the warning about survivorship bias. This goes beyond the annotations and is highly transparent.

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 and well-structured: a one-line summary followed by behavioral details, then clear 'Args' and 'Returns' sections. Every sentence adds value without redundancy, and the structure aids quick scanning.

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 description covers the tool's purpose, mechanics, parameters, return format, and important caveats (survivorship bias, cost estimates). Given the tool has a single complex parameter and an output schema, the description is complete and leaves no critical gaps.

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 includes descriptions for all parameters, and the tool description's 'Args' section lists them. The body adds meaning for 'period' (intraday cap) and 'top_n' (xs_momentum only), enhancing understanding beyond schema defaults. Schema coverage is formally 0% but descriptions exist, so baseline is 3 and the added context raises it.

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: 'Backtest a registered method by replaying its own analyze() over history.' It uses a specific verb and resource, and the details (bar-by-bar replay, daily vs intraday) distinguish it from sibling tools like quant_describe_method or quant_list_methods.

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 context on when to use the tool by explaining its mechanics (daily bar filling, intraday caps) and includes a caution to treat results as parameter validation. However, it does not explicitly state when not to use it or compare to alternatives, though the uniqueness of the tool makes it clear.

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

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

Annotations already mark the tool as readOnly, idempotent, and not destructive. The description adds valuable context: it returns upcoming events with null fields, the default window of 3 days, and the risk handling. 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 well-structured with a clear first sentence, usage guidance, and explicit Args/Returns sections. It is efficient and front-loaded, though slightly longer than minimal.

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 purpose and existing annotations/output schema, the description covers purpose, usage, and behavioral nuances. It explains how to use the output with another tool and what to do when data is missing, making it fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides descriptions for ticker and response_format. The description lists the same parameters in Args and adds return field names. While schema coverage is indicated as 0%, the schema actually has good descriptions, so the description adds 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 it provides 'Upcoming earnings and dividend events for a ticker,' specifying the action and resource. It distinguishes this tool from siblings like quant_score_decision by mentioning how to pass days_to_earnings to that 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?

The description explicitly tells when to use this tool (to check earnings/dividends before entries) and what to do with the output: pass days_to_earnings to quant_score_decision. It also advises checking the IR page when data is null, giving clear alternatives.

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, destructiveHint=false, idempotentHint=true, so the tool is clearly safe and non-destructive. The description adds valuable context about data sources (daily series for Hurst/ATR, intraday for VWAP/EMAs/RSI) and error handling ('Error string if no data'), which goes 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 very concise, with a clear structure: one-sentence summary, then details on data sources, followed by docstring-style args and returns. Every sentence is informative with no 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?

Given the complexity (multiple indicators, different timeframes) and the presence of annotations and schema, the description covers the essential behavioral aspects (data sources, return keys) and error behavior. However, it could mention prerequisites like market data availability or whether the ticker must be actively traded.

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% because the description only lists parameter names ('ticker, response_format') without adding any meaning beyond the schema's own descriptions. The schema already documents ticker as a required US equity symbol and response_format with enum, so the description adds negligible 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?

Description explicitly states the tool computes specific technical indicators (EMA9/EMA20, RSI, ATR, VWAP, Hurst exponent) for a ticker, with distinct action and resource. Sibling tools have clearly different purposes (e.g., analyzing setups, screening universes), so no confusion.

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 through the description of the tool's function (computing indicators), but there is no explicit guidance on when to use this tool versus alternatives like quant_analyze_setup or quant_detect_regime. No exclusions or prerequisites are mentioned.

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 provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. Description adds behavioral details: it returns an error string for unknown keys, and lists the return fields (name, paper, paper_url, regime_applicability, prose description). No contradiction.

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?

Description is extremely concise: one sentence plus an Args/Returns section. It front-loads the purpose and every sentence adds meaningful information. No fluff.

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 presence of an output schema, the description appropriately explains the return structure and error behavior. It also cross-references the sibling tool for key discovery. Complete for a read-only lookup tool with clear inputs and outputs.

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?

Despite 0% schema description coverage per context, the description mentions the key parameters (method_key, response_format) and the return format. It adds value by explaining how to handle errors and what the output contains, compensating for the noted 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?

Description clearly states 'Full detail and citation for one registered method', specifying verb (get detail), resource (method), and scope (one method, with citation). It distinguishes from sibling tools like quant_list_methods (which lists valid keys) and other analysis tools.

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?

Description explicitly advises to call quant_list_methods for valid keys if the key is unknown, providing guidance on error handling and an alternative tool. It implicitly tells when to use this tool (when you have a valid method_key and need full details).

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 behavioral context beyond the annotations by specifying the threshold logic, return value structure (dict with ticker, hurst, regime), and error handling for missing data. This complements the readOnlyHint and idempotentHint 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 concise and well-structured: a one-line summary, threshold logic, then args and returns. Every sentence adds value without 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?

Given the tool's low complexity (one parameter, clear annotations, and an existing output schema), the description sufficiently covers inputs, classification logic, output format, and error conditions. No additional details are necessary for correct usage.

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 good descriptions for the ticker and response_format fields. The description only briefly mentions 'Args: params (TickerInput): ticker, response_format,' adding minimal value beyond the schema. With schema coverage effectively high, 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 purpose: classify a ticker's regime from its daily Hurst exponent. It provides specific thresholds and regime labels, distinguishing it from sibling tools like quant_analyze_setup or quant_compute_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?

The description explains the classification logic and the conditions for each regime (trending, mean-reverting, random walk), providing clear context. However, it does not explicitly state when not to use this tool or suggest alternatives among 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, destructiveHint, and idempotentHint, which the description complements by detailing behavioral traits: 'Data only — no sentiment is computed' and 'deliberately does no interpretation'. It also specifies the return structure (title, summary, published, provider) and empty-list scenario, adding value beyond 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 concise with front-loaded main action, a brief behavioral note, and a structured Args/Returns section. Every sentence is informative and none are redundant, achieving good density of useful content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, the combination of description, schema, and annotations covers all essential aspects: purpose, usage guidance, parameters, return format, and integration with sibling tools. The mention of an output schema (even if not displayed) further supports completeness.

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 descriptions for ticker ('US equity symbol, e.g. NVDA') and response_format ('markdown for human-readable or json for machine-readable'). The description restates these fields but adds no new semantic detail. Since schema coverage is high, a 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 opens with 'Fetch recent headlines for a ticker', clearly stating the verb+resource. It further distinguishes itself by explicitly noting it does not compute sentiment, and directs the agent to use quant_score_decision for interpretation, making the 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 explicitly states when to use this tool: for raw data only, and instructs the agent to form its own sentiment and pass to a sibling tool (quant_score_decision). It also mentions the return format and empty-list handling, providing clear context for usage.

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 indicate readOnly, destructive=false, idempotent. The description adds details on return fields (key, name, paper citation, etc.) and behavior differences between markdown and JSON formats. No contradictions.

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 short (6 lines), with a clear first sentence stating purpose, followed by structured Args and Returns sections. Every sentence adds necessary information without 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?

Given an output schema exists (not shown but indicated), the description sufficiently explains the return values and references sibling tools. The parameter is well-documented. Slightly deduct for not mentioning pagination or limits, but overall complete for a listing 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?

The description reiterates the only parameter (response_format) with its enum values and explains how the return format differs between 'markdown' and 'json'. Since the schema description coverage is reported as 0% (though the schema actually includes a description for response_format), the description adds value by linking format choice to output style.

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 lists 'every registered paper-backed trading method', specifying the exact resource. It also distinguishes from siblings by mentioning it provides method_key values for quant_analyze_setup and quant_describe_method.

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 tells the agent to use this tool to discover valid method_key values for other tools, providing clear usage context. It doesn't explicitly state when not to use it, but the guidance is strong enough for correct selection.

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, destructiveHint=false, idempotentHint=true. The description adds value by specifying the exact output fields and format, but does not introduce behavioral traits beyond what annotations imply.

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 and well-structured: a one-sentence overview, a bullet list of content, and usage advice. Every sentence adds value, and the Returns section is clear.

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 description covers the output structure and usage context adequately. An output schema exists, so return values are not required. Minor gap: not explaining the breadth flag calculation in more detail, but sufficient for typical 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 input schema has one parameter (params) with a description for response_format in the schema. However, the tool description only repeats 'Args: params (FormatInput): response_format' without adding any new meaning. With 0% schema description coverage (as per context signals), the description fails to compensate.

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 it provides 'Index/VIX/sector tape read for the current session' and lists specific data like SPY/QQQ/IWM day %, VIX, sector rankings, and breadth flag. This distinguishes it from sibling tools like quant_analyze_setup or quant_detect_regime.

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 advises using this tool 'before sizing any intraday trade' and mentions a common failure mode (trading breakouts against risk-off tape). It does not explicitly state when not to use it, but the context is clear.

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

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

Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds valuable context: the tool is stateless (server stores nothing), computes heat/correlation/concentration, and returns a verdict for candidate trades. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with a one-line summary, then details usage and returns. The Args and Returns sections are clear. It could be slightly more concise but remains informative and well-organized.

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 complexity (nested objects, output schema exists), the description covers key aspects: statelessness, input requirements, output contents (heat, correlation, concentration, candidate verdict). It also references a sibling tool (quant_score_decision) for downstream 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?

Despite schema description coverage of 0%, the description explains the structure of positions and candidate (e.g., 'positions [{ticker, direction, entry, stop, shares}]'), adding meaning beyond what the schema provides. It also clarifies optionality and the equity parameter.

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 verb 'Assess portfolio risk' and the resource 'portfolio heat / correlation / concentration check'. It distinguishes itself from siblings like quant_analyze_setup or quant_backtest_method by focusing on risk evaluation, not analysis or backtesting.

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?

Description explains to pass open positions and optionally a candidate trade, and notes the stateless nature. It references the next step with quant_score_decision, providing context. However, it does not explicitly mention when not to use or list alternative 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 indicate readOnlyHint and idempotentHint. The description reinforces deterministic behavior ('Same inputs always yield the same output') and explains internal sub-factors and news veto logic. No contradictions; description adds valuable context beyond 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 well-structured with a clear purpose statement and separate Args/Returns sections. It front-loads the main action. However, some details (e.g., sub-factor list) could be more concise without losing essential 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?

Given the tool's complexity, the description covers inputs, outputs, and references to sibling tools. It explains the decision logic and return structure. Missing details like exact threshold or formula are reasonable omissions. The description is complete enough for an agent to understand usage.

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 includes detailed descriptions for all parameters (e.g., setup, equity, risk_pct). The description supplements this by summarizing how parameters combine into a composite score. While schema covers specifics, the description provides a high-level overview that aids understanding.

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 verb ('score and decide') and resource ('setup'), with the outcome 'ENTRY / NO_ENTRY'. It distinguishes itself from sibling tools by highlighting it is a pure function and decision helper, avoiding confusion.

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 the tool's role as a decision helper and mentions it is a pure function. It provides context on when to use it (after quant_analyze_setup) and how the agent should derive inputs like news sentiment. However, it does not explicitly state when not to use this tool over alternatives, leaving some ambiguity.

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, destructiveHint=false, idempotentHint=true. The description adds value by detailing the filtering criteria (under $5 or $50M volume), scoring formula, and output structure, which goes beyond basic safety hints.

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 with two well-organized paragraphs: first explaining purpose and algorithm, second detailing parameters and return. No unnecessary words. Front-loaded with the main action.

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 complexity (one complex parameter, annotations present, output schema exists), the description covers the algorithm, filters, scoring, and output format. It lacks edge cases (e.g., empty results) but is sufficient for selection and 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?

Input schema has 0% coverage for the top-level 'params' parameter, so the description must compensate. It lists the inner fields (tickers, top_n, response_format) and explains defaults, but the schema itself already provides these details. The added value is moderate.

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 verb 'Rank tickers' and specifies the resource (tickers) with a detailed methodology (intraday tradeability, hard-filters, scoring formula, top N). It distinguishes itself from sibling tools like quant_analyze_universe by focusing on screening with specific metrics.

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 does not provide explicit guidance on when to use this tool versus alternatives. No comparisons to siblings (e.g., quant_analyze_setup, quant_analyze_universe) or statements about when not to use it.

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