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

Discloses that it is draft-only, never changes live positions, requires OAuth write:drafts scope and Bullrun Pro account. This adds significant context beyond the annotations, which only indicate non-read-only and non-destructive.

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 relatively long but well-structured with key points front-loaded. Every sentence adds value, though it could be slightly more concise without losing 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 3 parameters, 100% schema coverage, and no output schema, the description covers prerequisites, behavior, interaction, and expectations. It is complete enough for an agent to use 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 coverage is 100%, so baseline is 3. Description adds extra context: explains that omitting prompt triggers user elicitation, and provides default values for maxPositions and startingCash. This adds value 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 clearly states the tool's purpose: building or proposing a brand-new portfolio by generating a reviewable draft. It uses specific verbs like 'BUILD' or 'PROPOSE' and distinguishes it from create_position_draft, which handles additions to existing portfolios.

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 says when to use (user wants a new portfolio) and when not to (use create_position_draft for existing portfolios). Provides guidelines for vague briefs, including asking one round of multiple-choice questions with defaults.

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?

Discloses draft-only behavior: 'saved to the user's account... never changes live holdings by itself'. Also mentions required OAuth scope and Bullrun Pro account. Annotation readOnlyHint=false and destructiveHint=false are consistent and complemented by this context.

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 well-structured with trigger, purpose, prerequisites, distinctions, and guidance. Each sentence serves a purpose; slightly long but earns its length. Could be more concise but effective.

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?

Covers purpose, prerequisites, behavioral constraints, alternatives, and disambiguation guidance. With no output schema, description provides sufficient context for agent to decide when and how 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?

Schema coverage is 100%, so baseline is 3. Description adds value by mentioning OAuth scope and Pro account requirement, and provides usage hints for clarifying portfolio and number of ideas. Does not repeat schema descriptions but adds overall parameter usage context.

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 generates 'REVIEWABLE suggested additions for one existing Bullrun portfolio' and uses specific trigger phrases like 'BUY' or 'ADD' to an existing portfolio. It distinguishes itself from sibling tools like create_portfolio_draft and get_portfolio_analytics.

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?

Provides explicit when-to-use triggers ('when the user asks what to BUY or ADD to an EXISTING portfolio'), when-not-to-use (use create_portfolio_draft for new portfolio, get_portfolio_analytics for specific ticker), and guidance for unclear cases (confirm portfolio and number of ideas).

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=true, and the description confirms "Read-only". The description adds that the tool returns "speaker-tagged" chunks and supports optional filtering, which goes beyond the annotation. No contradictions or missing critical behavioral traits (e.g., no pagination detail, but acceptable given the simplicity).

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: the first succinctly describes the action and options, the second explains the use case. Every word earns its place; 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?

The tool has 6 parameters (all documented in schema) and no output schema. The description explains the purpose and use case adequately. It could mention that results are ordered by speaker or time, but omitting that is a minor gap given the simplicity. The description is complete enough for an agent to understand what to expect.

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%, so baseline is 3. The description adds meaning by explaining the purpose of filtered chunks (qualitative judgment) and emphasizing the "exact Bullrun ticker" requirement. It also frames the optional filters (fiscal period, search text) in the context of finding specific transcript content, which helps an agent select parameters meaningfully.

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 "Fetch", the resource "speaker-tagged earnings-call transcript chunks", and the specific scope "for one exact Bullrun ticker". It distinguishes the tool from its siblings (which are portfolio, position, and financial metrics tools) by focusing on qualitative transcript data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent to use this for "management guidance language, analyst Q&A, and qualitative judgment that is not visible in financial statements". This provides clear context for when to invoke this tool over siblings like get_financial_history or get_forward_estimates. It does not explicitly state when not to use it, but the positive guidance is sufficient.

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

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

The annotations include readOnlyHint: true, so the description doesn't need to reiterate that. It adds behavioral context by describing the returned structure (groups like income statement, balance sheet, etc.) and mentioning consistency checks. This 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 a single, well-structured paragraph that front-loads the key action and details. Every sentence adds value: it states the fetch range, return types, data groups, and use cases. 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 absence of an output schema, the description compensates by listing the return data groups (income statement, balance sheet, etc.) and mentioning specific use cases. It provides a good sense of what the tool returns, though a bit more detail on the exact output format could improve 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?

Schema coverage is 100%, so parameters are well documented. The description adds meaningful context beyond the schema, such as specifying that tickers must be exact Bullrun tickers, explaining that annual rows use fiscalQuarter=0, and describing the nature of includeEmptyRows. This enriches the parameter 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 tool fetches historical financial statements for a Bullrun ticker, specifying the range (1-15 years), return types (annual/quarterly), and data groups (income statement, etc.). It distinguishes well from sibling tools like get_forward_estimates or get_quality_moat_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 explicitly says 'Use this when evaluating multi-year revenue/net-income growth, margin trajectories, leverage, cash flow quality, or whether a stock passed a rule such as 10% revenue and net-income growth every year.' This provides strong usage context, though it doesn't explicitly state when not to use it or name alternative tools for different purposes.

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 significant value beyond the readOnlyHint annotation by stating that the tool derives P/E and PEG context from the latest close, and it explicitly marks itself as read-only. 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?

Three sentences, each providing distinct value: core function, derived context, and read-only designation. No superfluous words; well front-loaded with the main purpose.

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 3 parameters and no output schema, the description covers the main return data (estimates, guidance, revisions, derived metrics). It lacks details on pagination or error handling, but these are not critical for basic 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?

With 100% schema coverage, the description does not need to repeat parameter details but adds context about the type of estimates (revenue, EPS, EBITDA) which relates to the output. It does not provide additional parameter syntax or behavior 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 explicitly states the verb 'Fetch' and the resource 'forward consensus revenue/EPS/EBITDA estimates' for a specific Bullrun ticker, clearly distinguishing it from sibling tools like 'get_earnings_call_transcript' or 'get_financial_history' which cover other data types.

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 clearly states it is for 'one exact Bullrun ticker', implying it should not be used for multiple tickers or other platforms. However, it does not explicitly exclude alternative uses or mention sibling tools for comparison.

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 annotation declares readOnlyHint: true, and the description repeats 'Read-only'. This is consistent and adds no contradiction. However, beyond that, the description does not disclose additional behavioral traits such as pagination, error handling, or rate limits. Given the annotation covers the safety profile, a score of 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 with no superfluous words. The first sentence conveys the purpose and examples, the second confirms idempotency. 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 no output schema, the description lists example metrics, which helps the agent anticipate return values. It also specifies that the ticker must be exact. It does not mention result ordering or pagination limits (though limit parameter exists), but overall it is complete enough for a read-only data retrieval 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%, so the schema already documents all parameters. The description lists example values for ticker, category, and metricKey but does not add significant meaning beyond the schema. The baseline of 3 is correct.

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 fetches operating KPIs and unit-economics metrics for a specific ticker, listing concrete examples like ARR, NRR, RPO. This distinguishes it from sibling tools that handle financial history, transcripts, etc.

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 says 'for one exact Bullrun ticker', implying a required ticker. It provides context about period-specific KPIs but does not explicitly state when to use this tool vs. alternatives like get_financial_history or get_forward_estimates. However, the examples differentiate it sufficiently.

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?

Discloses important behaviors beyond annotations: risk math drops unpriced holdings, coverage banner, privacyMode effects, OAuth requirements. Consistent with readOnlyHint annotation.

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?

Well-structured with use cases first, then technical details. Slightly verbose but all sentences add value. Could be tightened slightly.

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?

Despite no output schema, description thoroughly explains what analytics are returned (correlation matrices, contributions, exposures, scenario tests) and warns about coverage limitations.

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 already documents all parameters (100% coverage). Description adds context for candidateTicker and candidateWeightPct, explaining their purpose in candidate diversification analysis.

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 fetches portfolio-level relationship analytics for risk, diversification, concentration, and adding stocks. It distinguishes from sibling get_portfolio_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?

Explicitly states when to use (portfolio risk/diversification/concentration queries) and when not to (use get_portfolio_context for plain holdings snapshot).

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, so the description doesn't need to reiterate safety. However, it adds critical behavioral context: the response always returns a complete holdings list with matched/unmatched flags, a coverage summary, and warns against presenting matched-only figures as the whole portfolio. This is valuable beyond the annotation.

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 somewhat long but well-structured: usage guidance first, followed by response structure details, caveats, and alternative tool reference. Every sentence adds value, though it could be slightly tighter without losing clarity.

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 no output schema, the description fully explains the return shape (summary, holdings, insights, coverage banner). It also covers privacyMode and clarifies that holdings may lack weight/sector/insight for unmatched items. This is exceptionally complete for a non-trivial 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% (each parameter has a description). The description adds value by explaining portfolioId's origin ('from list_portfolios'), clarifying days as a look-back window, and illustrating privacyMode's effect on output format. This enriches the schema's baseline.

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 starts with explicit use cases ('Use when the user asks to look at, review, or analyze THEIR portfolio / holdings / positions') and provides concrete example queries. It clearly distinguishes the tool from siblings like get_portfolio_analytics by naming that alternative for risk/diversification analysis.

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 (portfolio review/analysis), when not to use for risk analytics (points to get_portfolio_analytics), and instructs to call list_portfolios first if portfolio ID is unknown. This provides clear decision 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 declare readOnlyHint=true. The description goes beyond by listing computed metrics, explaining parameter effects (e.g., WACC fallback, tax-rate fallback), and stating it uses existing financial statements. 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 efficient: two sentences that immediately state purpose, list metrics, and note read-only nature. No fluff, well front-loaded.

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 complexity (4 params, no output schema), description covers purpose, metrics, parameter behavior, and read-only nature. It does not specify the output format or structure, which would be helpful for an agent, but overall it is 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?

Schema covers 100% of parameters with descriptions. The description adds value by explaining that ROIC-vs-WACC spread returns null when WACC is omitted and that taxRateFallbackPct only used when reported data missing. This enhances understanding beyond 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?

Description clearly states the tool computes annual quality and moat metrics for a single Bullrun ticker, listing specific metrics (ROIC, ROE/ROA, etc.). This distinguishes it from siblings like get_financial_history or get_stock_metrics, which handle raw data or different analyses.

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 does but does not explicitly state when to use it versus alternatives or when not to use it. It implies usage for a single ticker but lacks guidance on context or exclusion.

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 the description confirms 'Read-only.' Beyond that, it adds minimal behavioral context (e.g., no mention of rate limits, pagination, or error handling). The description is adequate but does not significantly enrich behavioral transparency 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?

Two sentences front-loaded with action and resource, followed by usage guidance and a read-only note. Every sentence adds value 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 tool's simplicity (3 parameters, no output schema), the description covers what, when, and safety. It could mention that return format is an array of rows, but that's implicitly understood from 'rows'. Slightly incomplete but largely sufficient.

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 baseline is 3. The description mentions the dimension types (segment, geography, etc.) but the schema already defines them via an enum. No additional parameter semantics beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The verb 'Fetch' and specific resource 'revenue breakdown rows for one exact Bullrun ticker' clearly state the tool's function. It distinguishes from siblings like get_financial_history by focusing on revenue breakdowns and exact ticker-level data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly provides use cases: 'separate cyclical businesses from recurring segments or inspect geographic exposure instead of relying on blended revenue.' This gives strong context for when to use, though it lacks explicit when-not-to-use or 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 declare readOnlyHint=true, and the description adds 'Read-only', confirming no side effects. The description details exactly what data is returned, but does not discuss rate limits, data freshness, or authorization requirements. The transparency is good but not exhaustive.

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: two sentences. The first sentence efficiently lists all data categories, and the second provides a critical usage instruction. No redundant or filler 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 complexity (multiple metric categories) and the absence of an output schema, the description adequately enumerates the returned data (identity, price, valuation, financials, description). It does not specify data structure or units, but the categories are sufficient for an AI agent to understand the tool's output.

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% for the single parameter (ticker), with a clear description. The description adds value by reiterating the ticker format and providing examples (e.g., AAPL, ABBN.SW), which helps disambiguate usage 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 explicitly states the tool fetches a consolidated metrics snapshot for a single stock by ticker, listing specific categories (identity, price, valuation, financials, description). This clearly distinguishes it from sibling tools like get_financial_history or get_earnings_call_transcript, which focus on narrower aspects.

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 includes a usage guideline to use the exact ticker as listed on Bullrun with Yahoo-style suffixes, providing examples. While it does not explicitly state when not to use this tool or compare to alternatives, the broad snapshot nature implies it is for a quick overview, and the parameter guidance 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 provide readOnlyHint=true, and description adds OAuth requirement, user-specific data limitation, privacyMode behavior, and read-only nature. 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?

Well-structured with purpose first, then details. Slightly verbose but every sentence adds value. Could be shortened without loss.

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?

Covers all necessary aspects: purpose, prerequisites (OAuth), return value, parameters, privacy mode, and relationship to sibling tools. No output schema needed for this list operation.

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?

Only one parameter (privacyMode) with 100% schema coverage. Description adds context beyond enum values: explains defaults and effect on returned data. Slightly redundant with schema description but clear.

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 uses specific verb 'list' and resource 'portfolios', explains it returns computed summaries, and distinguishes from siblings by stating 'start here when a portfolio question doesn't name a specific portfolio'.

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 (user refers to 'their' portfolios/holdings) with examples. Provides clear context: start here, then pass portfolioId to get_portfolio_context/analytics. Does not mention when not to use or list alternatives, but the guidance 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=true, so no destructive behavior. Description adds return details (profile, prices, holdings) but no further behavioral traits like rate limits or permissions. 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?

Two sentences, front-loaded with core functionality, no fluff. Every sentence 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?

Despite 13 parameters and no output schema, the description gives a clear overview of search capabilities and exact-ticker returns. Could elaborate on output structure, but current level is adequate.

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 each parameter individually described. The tool description provides some context (e.g., 'maps to Bullrun's ETF focus column') but doesn't significantly add beyond the schema. 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?

Description uses specific verb 'Search' and resource 'Bullrun ETF universe', lists search criteria (ticker/fund name, category, focus, domicile, exchange, currency), and distinguishes exact-ticker returns (profile, prices, holdings). It also states 'Read-only', aligning with annotations.

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?

Clearly states when to use (searching ETFs) and what inputs are available. Does not explicitly mention when not to use or alternatives among siblings, 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 declare readOnlyHint=true, and the description reinforces this with 'Read-only'. It adds context about using the same rule engine as the app screener and returning a compact table, which is helpful beyond the annotation.

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 that capture the tool's purpose, scope, and result type. Every word adds value, 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 (15 parameters, no output schema), the description provides a solid overview. The schema handles detailed parameter info. It could mention default values or array behavior, but overall it's reasonably 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?

Schema coverage is 100%, but the description synthesizes the parameters into a coherent narrative (e.g., 'AND/OR rule groups', 'comparison operators', 'money units'). This adds meaning beyond individual parameter descriptions, earning a 4.

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 screens the Bullrun stock universe using the same rule engine as the app, and lists the many filtering criteria. It distinguishes itself from sibling tools like get_stock_metrics and query_etfs by focusing on screening with complex rule logic.

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 explains when to use this tool (to filter stocks by various criteria), but does not explicitly contrast with alternatives or state when not to use it. The context is clear enough for an agent to decide, but lacks explicit exclusions.

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