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

Annotations already declare readOnlyHint=true, and the description adds behavioral context by specifying the time scope (current/most recent session) and the metrics returned, which enhances transparency without 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 concise (two sentences), front-loaded with purpose, and includes all necessary information without extraneous text.

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 single parameter and the presence of an output schema, the description sufficiently explains the return metrics. It is complete for a simple 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% with a single parameter 'ticker' well-described. Description does not add additional semantics beyond the schema, so baseline score 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?

Description clearly states it retrieves intraday accumulation/distribution metrics for the current or most recent trading session, listing specific metrics like VWAP, volume above/below VWAP, etc. It is distinct from sibling tools which focus on 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?

Provides a usage context ('Use for assessing real-time buying/selling pressure') but lacks explicit when-not-to-use or alternative tools. Implied usage is reasonable but no exclusions or comparisons.

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?

Description matches readOnlyHint annotation (no contradiction). It adds value by specifying the data fields returned, 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: first states purpose and data, second gives usage guidance. No waste, front-loaded with 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 simplicity (one required parameter, has output schema), the description covers purpose, returned data, and usage guidance completely.

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 description does not need to add parameter details. The schema already describes 'ticker' well. Description does not provide extra parameter-level information.

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 gets analyst consensus for a company, listing specific data points (average target price, number of analysts, buy/hold/sell breakdown, consensus recommendation). It distinguishes itself from sibling tools like get_price_target and get_analyst_estimates.

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 'Use when evaluating Wall Street sentiment or price targets.' Provides clear context, though no explicit exclusions or alternative tools 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 declare readOnlyHint=true, so the description's role is limited. It adds that the tool provides grades, targets, and coverage breadth, but lacks details on data recency, pagination, or number of firms. It does not contradict 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, well-structured sentence that front-loads the action ('Get aggregated analyst coverage') and concisely explains the output. No superfluous 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 tool's low complexity (one required parameter, annotations provided, output schema exists), the description sufficiently explains the tool's purpose and output. It does not need to detail return values since the output schema covers that.

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 is only one parameter (ticker) with schema description coverage at 100% (it describes the ticker symbol format). The description does not add additional semantic meaning beyond the schema, so 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: 'Get aggregated analyst coverage for a ticker — consolidated view of grades, targets, and coverage breadth across covering firms.' It uses a specific verb and resource, and distinguishes itself from siblings like get_analyst_consensus, get_analyst_estimates, and get_analyst_grades by highlighting aggregation and breadth.

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?

No explicit guidance on when to use this tool versus alternatives. The description implies an aggregated view but does not specify situations where this is preferred over individual analyst tools. No 'when not to use' or mention of prerequisites.

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

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

Annotations already declare readOnlyHint=true, so the description doesn't need to cover safety. It adds the behavioral context of returning forward estimates with specific metrics. No contradictory or missing behavioral details, but doesn't discuss rate limits or performance.

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 purpose and key details, immediately followed by usage guidance. No wasted words or redundant information. Perfectly concise for an AI agent.

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 output schema exists (not shown but implied), the description adequately covers the return content and period options. It doesn't mention pagination or error handling, but for a straightforward financial data tool, it is sufficiently 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 description adds meaning beyond the schema by explaining that estimates include low/high/avg and analyst counts. Schema coverage is 100%, so baseline is 3; the description enriches it further with context about the returned data fields.

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 'Get forward analyst estimates for a company' and lists specific metrics (EPS, revenue, EBITDA, net income) with low/high/avg and analyst counts. It distinguishes from sibling tools like get_analyst_consensus by implying it provides detailed estimates rather than a single consensus figure, though not explicit.

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 direct usage suggestion: 'Use when analyzing forward earnings expectations or revenue forecasts.' This gives clear context. However, it does not mention when not to use it or provide alternatives, which would be helpful given 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, indicating a safe read. The description adds that it returns 'recent' actions, providing temporal context. No contradictions, and the added context is valuable but could specify ordering or depth of recency.

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 of 14 words that efficiently conveys purpose and output scope with no unnecessary details.

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 retrieval tool with an output schema (context indicates present), the description covers the key aspects: what actions, for which ticker, and what fields are returned. It is sufficiently complete without needing to explain return values in prose.

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 adequately described in the schema. The description adds minimal parameter-specific meaning beyond mentioning 'for a ticker' and the types of grades in the output.

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 gets recent analyst grade actions (upgrades, downgrades, initiations) for a ticker and lists included fields (firm, previous/new grade). It distinguishes from siblings like get_analyst_consensus and get_analyst_estimates by specifying actions.

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 use for retrieving ticker-specific analyst grade changes but does not explicitly state when to use this tool vs alternatives (e.g., get_price_target, get_analyst_consensus) or provide exclusions.

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?

Beyond the readOnlyHint annotation, the description discloses deduplication logic (annual preferred over quarterly) and chronological sorting. It also mentions the return structure, providing rich behavioral 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?

Three concise sentences deliver core functionality, return format, dedup logic, and feature-gating. 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?

Given the output schema exists, the description appropriately provides a high-level overview of the output structure. It covers source, range, dedup, and access constraints, making it complete for a simple one-parameter 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%, but the description adds value by stating the ticker must correspond to a company with SEC filings, which conditions the parameter's validity. This goes beyond the schema's generic ticker description.

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

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

The description clearly states it retrieves up to 10 years of quarterly cash position history from SEC XBRL filings, specifying data source, time range, frequency, and output format. It uniquely identifies the tool's purpose among siblings like get_cash_position and get_cash_runway_calendar.

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 it's not feature-gated and works for any company with SEC filings, providing clear context for when to use it. While it doesn't name exclusions or alternatives, the unique purpose differentiates it from 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, indicating a safe read operation. The description adds value by listing specific output fields (cash anchor, burn rate, capital raises, runway scenarios) and the error condition (404), providing clear behavioral expectations 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 concise with four focused sentences. It is front-loaded with the purpose. No content is wasted, but it could be slightly more compact. A score of 4 reflects good efficiency without being the absolute minimum.

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 (single parameter, existing output schema, annotations present), the description covers the purpose, usage, return values, and error condition comprehensively. There are no missing critical details for an agent to invoke this 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 input schema has 100% coverage for the single parameter 'ticker', with a clear description. The tool description does not add any additional parameter semantics beyond what the schema already provides, so 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 verb 'Get' and the resource 'Signal8 AI cash position model', and enumerates return data. However, it does not explicitly distinguish itself from sibling tools like get_cash_history or get_cash_runway_calendar, so it falls short of a 5.

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 explicit usage context: 'Use when analyzing a company's current cash situation, runway, or capital raise activity.' It also notes the 404 condition. However, it does not mention when not to use the tool or suggest alternative tools, so it does not achieve 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, but the description adds valuable context that the runway is an estimate based on current burn rate and depends on future events, going 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 with no wasted words. Core function is front-loaded, followed by defaults and caveats.

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 moderate complexity, full schema coverage, and the existence of an output schema, the description provides sufficient context about purpose, sorting, defaults, and the estimate nature of the runway.

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

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

Schema coverage is 100%, and the description does not add per-parameter details beyond the schema. Baseline score of 3 is appropriate as the schema already documents parameters well.

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 finds companies projected to run out of cash within a date window. It distinguishes itself from sibling tools by comparing to lockup expiration calendars and specifying it's for cash depletion events.

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 (finding companies running out of cash) and mentions default window, but lacks explicit when-not-to-use or alternatives 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 declare readOnlyHint=true, so the safety profile is clear. The description adds no further behavioral details such as pagination, data freshness, or limitations. Since annotations already cover the key behavior, the description provides minimal added value beyond the structured field.

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 key purpose, and contains no redundant or extraneous words. Every part contributes to understanding 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?

Given the presence of an output schema (not shown but indicated) and a simple parameter set, the description provides sufficient context for using the tool. It could mention that it returns a list of trials with specific fields, but overall it is adequate for a straightforward retrieval tool. The sibling search_clinical_trials might require more differentiation, but the current description still offers good 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 description coverage is 100%, with both parameters (ticker, limit) documented. The tool description mentions output fields (trial phase, status) but not parameters. It adds little additional meaning beyond what the schema already provides for the parameters, justifying the baseline score of 3.

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 (Get), resource (clinical trial data), and context (for a biotech/pharma company), listing included data fields like trial phase and conditions. However, it does not explicitly differentiate from the sibling tool search_clinical_trials, which likely performs a similar but search-oriented function.

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 use context ('when analyzing a biotech company's pipeline or upcoming catalyst events'), but does not give when-not-to-use guidance or contrast with the sibling search_clinical_trials. The usage scenario is implied but not explicit about 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?

The description adds behavioral details beyond the readOnlyHint annotation: it explains the tool returns trading-halt status fields (halted/haltCode/haltedAt) and clarifies the behavior when trading normally (false/null). It also states this is a 1-credit operation, providing cost 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?

The description is two sentences, efficient and front-loaded. Every sentence adds value: first sentence states purpose and outputs, second sentence provides usage guidance and behavioral note.

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 is a simple lookup with one parameter and an output schema exists, the description covers all essential aspects: what it does, when to use, what it includes, and a special behavioral note about trading halt status.

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 single parameter ticker with a clear example. The description does not add deeper semantic meaning to the parameter but reinforces its purpose. With 100% schema coverage, 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 it retrieves an enriched company profile using a ticker symbol and lists specific returned fields (CIK, exchange, sector, etc.). It also distinguishes from a 'full bundle' tool, helping the agent understand its scope.

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 advises using this for basic company info rather than the full bundle, and notes it is a lightweight lookup (1 credit). It does not explicitly name a sibling tool for the full bundle but provides clear guidance on when to use this tool.

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 annotations: it discloses the 25-credit cost, the comprehensive nature (combining SEC, market, and exchange data), and the fact it runs multiple compliance checks. This enriches the readOnlyHint annotation without 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?

The description is two sentences front-loaded with the core purpose, followed by details on what it covers and a cost 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 presence of an output schema (so return values are documented elsewhere) and 100% schema coverage for the single parameter, the description is complete. It explains what the tool does, its scope, and cost, providing sufficient context for an AI agent.

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 one parameter 'ticker' described as 'Stock ticker symbol.' The description adds no additional meaning beyond the schema, 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 clearly states the tool's purpose: 'Get full compliance rules evaluation for a company.' It specifies what it runs (Nasdaq/NYSE deficiency detection, bid price tracking, delinquent filing detection) and what it combines (SEC filing data, market data, exchange rules), making it distinct from siblings like get_insider_transactions or get_filing_document.

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 the most thorough compliance check, with a cost of 25 credits. It provides context about the scope but does not explicitly state when to use vs. alternatives or when not to use it. A brief mention of when to prefer this over lighter tools would improve it.

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. Description adds context about aggregate nature and included breakdowns. No contradictions, but could mention data recency or scope ('ALL tracked politicians') more precisely.

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 specifies purpose and outputs, second provides usage guidance and sibling differentiation. No extraneous 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 read-only nature, optional parameters with defaults, and clear output description, the definition fully equips an agent to select and invoke this 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?

Schema coverage is 100% with clear parameter descriptions. The tool description adds minimal extra semantic value beyond what schema already provides (e.g., default cycle behavior). 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 it retrieves market-wide campaign-finance rollups across all tracked politicians for a cycle, listing specific outputs (total raised, top donors, splits, leaderboard). It explicitly distinguishes from sibling tool get_politician_donor_summary.

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 use cases ('who are the biggest donors in 2024?') and contrasts with alternative for single politician ('For a single politician, use get_politician_donor_summary').

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, so description need not reiterate. Description adds output specifics but no additional behavioral traits like pagination or rate limits. Adequate for a read-only tool.

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 concise sentences, front-loaded with purpose. 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?

Tool is simple with 2 parameters and an output schema. Description adequately covers purpose and output content. Could mention data range or default limit, but 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 coverage is 100% with both parameters documented. Description does not add parameter-level meaning beyond what schema provides. Baseline score 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?

Description clearly states it gets historical earnings data with specific fields (EPS, revenue, surprise percentages). However, it does not explicitly differentiate from sibling tools like get_analyst_estimates or get_earnings_calendar.

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: analyzing earnings beats/misses or upcoming expectations. Lacks when-not-to-use or alternative suggestions, but the provided context is adequate.

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 indicate readOnlyHint=true, and the description adds behavioral context by listing the returned fields and filter capabilities. It does not conflict with annotations, and the added detail (market cap filtering, specific data fields) is valuable for safe usage.

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 three sentences, front-loaded with the main action, and every sentence adds value. 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?

Given the presence of an output schema, the description sufficiently covers the tool's capabilities: date range, ticker filter, market cap filter, and returned fields. No critical information is missing 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?

With 100% schema coverage, the description adds meaning beyond the schema by explaining the purpose of date range parameters and how market cap filtering works (e.g., 'focus on large-cap or small-cap earnings only'). This enhances understanding of parameter usage.

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 retrieves upcoming and recent earnings releases between two dates, with optional ticker and market cap filters. It specifies the returned fields (ticker, date, time, EPS estimate, revenue estimate), making the purpose distinct from sibling tools like get_earnings or get_economic_calendar.

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 (earnings calendar between dates, with optional filters) but does not explicitly mention when not to use or suggest alternatives. It lacks exclusionary guidance compared to 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 readOnlyHint=true, indicating a safe read operation. The description adds that events are scheduled and date ranges are inclusive, but does not disclose additional behavioral traits such as rate limits or pagination. Given the annotation coverage, the description adds minimal extra value.

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 with no redundant words. The first sentence captures the core purpose and the second adds optional filter and default. Perfectly front-loaded and 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?

With an output schema present, the description does not need to explain return values. It covers the essential aspects: date range, country filter with default, and examples of event types. For a tool with 3 parameters (2 required) and an output schema, the description provides complete contextual guidance.

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 detailed parameter descriptions. The tool description adds the default country behavior ('Defaults to US when omitted'), which is extra semantic information beyond the schema. This aids the agent in correctly invoking the tool.

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

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

The description clearly identifies the tool as retrieving scheduled macro/economic events with a specific verb 'Get' and a resource clearly defined. It lists example events (CPI, FOMC, etc.) and specifies date range and optional country filter, making it easy to distinguish from sibling tools that handle different 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 provides clear context: when to use it (to get economic events between dates) and includes a default behavior (countries default to US). However, it does not explicitly exclude alternatives or contrast with similar tools like get_earnings_calendar, leaving some ambiguity for edge cases.

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. Description adds independent caching per data type and the bundling behavior, providing useful 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?

Four sentences, each with a purpose: purpose, data sources, caching, usage guidance. No redundancy, 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?

Output schema exists, so return values are documented. Description covers data types, caching, and usage. Lacks mention of prerequisites or rate limits, but sufficient for a read-only bundle 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 covers both parameters with descriptions (100% coverage). The description adds context about include defaults and comma-separated format, but doesn't add entirely new meaning 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?

The description clearly states it aggregates multiple ETF data sources into one call, explicitly listing the types (profile, holdings, etc.) and distinguishing it from individual siblings like get_company_profile.

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?

Describes when to use (for aggregated data) and how to customize with include/omit, but does not explicitly state when not to use or mention alternatives like individual getters.

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

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

The annotations already mark readOnlyHint=true, so the description's statement is consistent. However, no additional behavioral traits (e.g., pagination, permission needs) are disclosed 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?

Two sentences, front-loaded with purpose and usage; every word is necessary and no 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?

Given the simple input schema and presence of an output schema, the description is sufficient. It hints at output fields (name, title, compensation, tenure) which compensates for not detailing the return structure.

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

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

Schema coverage is 100% for the single parameter 'ticker', with a clear description. The tool description adds no extra meaning 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 description uses a specific verb 'Get' and resource 'key executives and officers'; it clearly identifies the data fields (name, title, compensation, tenure) and distinguishes from siblings like get_insiders by focusing on top executives.

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 (researching company leadership or management quality) but does not mention alternatives or when not to use, leaving the agent to infer from the sibling list.

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

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

Annotations already declare readOnlyHint=true, so the description adds value by explaining truncation behavior and the truncated boolean in the response. 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?

Three concise sentences: purpose, return fields, usage hint. No filler, 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?

With an output schema present, the description covers input, usage, and behavior fully. No missing information for an AI agent to use 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?

Schema coverage is 100% with clear descriptions. The description adds context about maxLength truncation and the truncated response field, going 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?

The description clearly states it gets the full text/HTML content of a single exhibit from an SEC filing, with a specific verb and resource. It distinguishes from siblings by referencing get_filing_exhibits for finding IDs.

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 explicitly instructs to use get_filing_exhibits first to find exhibit IDs and mentions the maxLength parameter for truncation. While it doesn't list when not to use, the guidance is clear 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 declare readOnlyHint=true, consistent with the read nature. The description adds behavioral context: it returns a forward-looking calendar, default date ranges, and default form types. 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?

Two sentences that are direct and contain no extraneous information. Every word 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?

Given the presence of an output schema, full parameter coverage, and read-only nature, the description is complete. It covers purpose, optional filters, and default behavior, leaving 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?

Schema coverage is 100% with parameter descriptions. The description adds meaning beyond schema by clarifying it is forward-looking and specifying default behavior (both 10-K and 10-Q). This helps the agent understand default values without inspecting schema defaults.

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 retrieves a forward-looking SEC filing deadline calendar specifically for 10-K and 10-Q forms. It uses a specific verb ('get') and resource ('filing calendar'), distinguishing it from sibling tools like get_earnings_calendar or get_economic_calendar.

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 optional filters (universe and formTypes) and default behavior (both 10-K and 10-Q). It implicitly guides when to use this tool (when needing 10-K/10-Q deadlines) but does not explicitly state when not to use it or mention 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?

Discloses that filings can be very large (10-K up to 1MB+) and explains truncation behavior via maxLength, including the truncated boolean in the response. This provides behavioral benefits beyond the readOnlyHint annotation, which already indicates no side effects.

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, no redundancy. The first sentence states the core purpose, followed by size warning, preview guidance, and response fields. 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?

Given the output schema exists, the description sufficiently covers return fields and behavior. With only 2 parameters and clear annotations, the description is complete for an AI 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?

Schema covers both parameters (filingId, maxLength) with basic descriptions. The tool description adds value by clarifying filingId is numeric and must come from search_sec_filings, and that maxLength triggers a truncated boolean in the response. It enriches the schema but could be more explicit about expected formats.

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 retrieves raw text/HTML content of an SEC filing by its internal filing ID, specifying the verb (Get), resource (filing document), and key context (returns company_name, form_type, etc.). This distinguishes it from sibling tools like search_sec_filings or get_exhibit_content.

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 to find filing IDs using search_sec_filings first and mentions maxLength for previews. While not listing alternatives or when-not-to-use, this guidance is clear and contextually sufficient given the 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 mark this as read-only. The description adds behavioral context by stating it excludes XML/XBRL exhibits and returns metadata (not full content), which clarifies the tool's scope 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 two sentences long, front-loaded with the primary action, and every sentence adds value: listing purpose, return content, and usage guidance. 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 tool is a simple listing operation with read-only annotations, an output schema (not detailed but present), and clear parameter description in schema, the tool description provides all necessary context: what it does, what it returns, how to use it next, and what it excludes.

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% description coverage for the only parameter (filingId), referencing sibling tool search_sec_filings. The tool description does not add new meaning beyond the schema; it mentions 'within an SEC filing' but does not elaborate on the parameter itself. 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 lists exhibits within an SEC filing, returns metadata (type, description, size), and explicitly excludes XML/XBRL exhibits. It distinguishes itself from get_exhibit_content by positioning this tool as a discovery step.

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 identify which exhibits to read with get_exhibit_content, providing clear usage context. It also notes that XML/XBRL exhibits are excluded, hinting at alternatives. However, it does not address when not to use this in favor of other sibling tools like get_filing_document.

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 the description does not contradict. However, beyond stating the data types and periods, it offers no additional behavioral context (e.g., data source, update frequency, pagination), so it adds minimal value 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?

Two efficient sentences with no wasted words. The first sentence states the action and resource, the second specifies use cases, making it 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 presence of an output schema (mentioned in context signals) and the clear description of the financial statements and period types, the description is complete for an agent to understand what the tool returns and when to use it.

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

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

Schema coverage is 100%, so the baseline is 3. The description echoes the type parameter's enum values but adds no new meaning for 'ticker' or 'limit' beyond what is in the schema. It does not explain default behavior or constraints 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 it retrieves income statement, balance sheet, and cash flow data, with explicit period options (annual, quarterly, TTM). This distinguishes it from sibling tools like get_earnings or get_cash_history, providing a specific verb-resource pair.

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 'Use when analyzing revenue, profitability, debt, or cash position,' giving clear context for when to invoke the tool. However, it does not mention when not to use it or suggest alternative tools for related but distinct data (e.g., cash history), missing an opportunity for explicit exclusion 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?

The description adds context beyond the readOnlyHint annotation by specifying the exact data fields returned. No destructive behavior is implied, and no contradictions exist.

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 wasted words. It front-loads purpose and includes usage guidance efficiently.

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 low complexity (1 param, no nested objects, output schema exists), the description fully covers what the tool does and when to use it.

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

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

Schema coverage is 100% with a clear description for the ticker parameter. The description does not add additional meaning beyond the schema, 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 clearly states the verb (Get), resource (float and share structure data), and lists specific data points (shares outstanding, public float, insider ownership %, institutional ownership). It distinguishes from siblings like get_ownership and get_insider_transactions by focusing on float-specific 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 says 'Use when analyzing share supply and ownership concentration,' providing clear context. It doesn't mention when not to use or suggest alternatives among siblings, but given the specific purpose, it's adequate.

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. Description adds behavioral context: returns candle format, supports multiple resolutions, default period of 1 year. Adds value beyond annotations without 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 succinct sentences. First sentence states main purpose and resolution options. Second sentence covers period flexibility and use cases. No wasted words. Front-loaded with key info.

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?

Output schema exists, no need to explain returns. Description covers purpose, usage, parameter behavior, and example use cases. Complete for a data retrieval tool with good annotations.

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 has 100% parameter descriptions. Description adds significant extra meaning: explains period shorthand values, default behavior (1Y daily), that from/to override period, resolution default. This goes well 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?

Clearly states verb 'Get' and resource 'historical OHLCV price candles for a stock'. Lists supported resolutions and specific use cases (compute returns, chart, analyze volume). Distinguishes from siblings like get_intraday_bars and get_quote by specifying resolution and period options.

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 clear context for when to use: computing returns, charting, volume analysis. Explains period vs from/to timestamp usage. Doesn't explicitly exclude alternatives but given sibling count, context 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?

Annotations indicate readOnlyHint=true, and the description elaborates on the analysis performed: identifies clusters with specific criteria (3+ insiders, 14-day window) and interprets the signal as bullish. No contradictions; adds valuable behavioral detail 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?

Two sentences: first states the core function, second details the criteria and implication. Every sentence adds value; no wasted 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 simple single parameter and existence of an output schema, the description fully covers the tool's purpose, criteria, and significance. No 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 single parameter 'ticker' is fully described in the schema with an example. The description does not add any additional semantic meaning or constraints beyond what the schema provides. Baseline 3 due to 100% schema 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?

Description clearly states the tool detects cluster buying patterns for a company, specifying the trigger condition (3+ distinct insiders within 14 days) and its significance as a bullish signal. This distinctively separates it from sibling tools like get_insider_transactions.

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 (to identify bullish insider clusters) but does not explicitly state when not to use or suggest alternatives. It implies use for predictive signals, which is clear enough among many insider 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?

Adds context beyond readOnlyHint: describes searching entire universe, detecting networks and clusters. 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?

Three concise sentences, front-loaded with purpose and differentiation, 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 output schema exists and all parameters described, the description adequately explains the tool's unique value, use cases, and scope. No need to elaborate on return values.

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. Description mentions filtering by name, type, date range which aligns with schema but does not add new meaning beyond what schema already provides.

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

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

Clearly states the verb 'discover' and resource 'insider trading patterns across multiple companies'. Distinctly differentiates from sibling get_insiders which focuses on a single ticker.

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 contrasts with sibling get_insiders, guiding when to use this tool (cross-company) vs single-ticker. Mentions filtering options but lacks explicit 'when not to use' scenarios.

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 indicate readOnlyHint=true, and the description adds that data is derived from Form 4 filings, includes a lookupMode field, and explains the fallback logic (issuer first, then insider). This adds meaningful context 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 three concise sentences. The first sentence is the main purpose, followed by two sentences that add necessary nuance. 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 tool's dual behavior and the presence of an output schema (not detailed), the description adequately explains both use cases, the lookupMode field, and the data source. It is complete for an agent to understand the tool's functionality.

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 cik parameter with a description, but the tool description adds the dual interpretation logic (issuer vs. insider) and the fallback behavior, providing significant additional 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 retrieves current open insider positions for a CIK, distinguishing between issuer and insider interpretations. It uses a specific verb 'Get' and identifies the resource as 'insider positions', differentiating it from siblings like get_insider_positions_by_ticker.

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 when to use each CIK type (issuer vs. insider) and implies that for ticker-based lookups, other tools like get_insider_positions_by_ticker should be used. While not explicit about alternatives, it provides clear context for the two primary use cases.

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?

Adds context beyond readOnlyHint: explains it returns lifetime aggregates of cost/value and source (Form 4). 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 core purpose, second sentence adds source. 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 output schema exists and the tool has only one parameter, the description sufficiently explains purpose, source, and output nature. No missing critical info.

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 'ticker'. Description repeats 'given ticker' but adds no extra meaning. 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?

Clearly states it gets 'per-insider lifetime position aggregates' for a given ticker, differentiating from sibling tools like get_insider_positions and get_insider_transactions. Verb and resource are specific.

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

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

Implies usage for aggregate insider positions per ticker, but no explicit when-not-to-use or alternative tools mentioned. Context from 'Derived from Form 4' helps, but guidance is minimal.

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 valuable behavioral context: explains transaction breakdown by SEC code, fields like netSharesSold12m and isPrimarilyTaxWithholding, and pagination support. 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 a single, well-structured paragraph that front-loads the purpose and efficiently conveys all necessary details without unnecessary repetition. 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?

Given the complexity of insider data, the description covers key aspects (cluster buying, transaction breakdown, flags, pagination) and leverages the output schema. It feels complete for an AI agent to understand what data 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%, and the description merely reiterates the parameters (ticker, limit, offset) without adding significant new information beyond what the schema already provides. Baseline 3 is appropriate.

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

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

The description clearly states 'Get insider trading discovery data for a company' and lists specific features like cluster buying detection, entity-centric insider model, and Form 4 cross-referencing, distinguishing it from sibling tools such as get_insider_transactions which focus on raw transactions.

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 comprehensive insider analysis but does not explicitly state when to use this tool versus alternatives like get_insider_transactions or get_insider_positions. There is no direct guidance or exclusions.

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 include readOnlyHint: true, and description aligns with read-only behavior by stating 'Returns individual buy/sell transactions.' Discloses pagination and filtering behavior beyond annotations. 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?

Two concise sentences with key information front-loaded. Every sentence adds value, no wasted words. Structure is efficient and easy to parse.

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 6 parameters, output schema present, and no nested objects, the description fully covers the tool's capabilities: pagination, filtering by year/month/transactionCode, and the use case. Nothing essential is missing.

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

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

Schema coverage is 100% with descriptions, but description adds value by explaining transactionCode with examples (P=Purchase, S=Sale, etc.) and clarifying that month requires year. This enhances 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?

Description clearly states 'Get detailed insider transaction history for a company from Form 4 filings' with specific verb and resource. It also lists what is returned (insider name, title, shares, price, transaction codes), distinguishing it from sibling tools like get_insider_positions or get_insider_cluster_buys.

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 guidance on when to use: 'Supports pagination for companies with extensive insider activity' and 'Filter by year/month... use transactionCode to find only purchases...' Includes a use case: 'Useful for identifying first insider buy since X patterns.' Does not explicitly state when not to use, but context from sibling tools 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?

The annotations already declare readOnlyHint=true, indicating a safe read operation. The description adds 'Reads the number of trailing periods to include,' which clarifies parameter behavior but does not disclose additional traits like data source frequency or response format. With annotations present, the description provides adequate but minimal extra 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?

Two concise sentences: the first states the core purpose with specific verbs and resources, and the second adds a brief parameter note. No unnecessary words, front-loaded with key info. This is an exemplary efficient description.

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 (2 parameters, output schema exists), the description covers the essential purpose and parameter roles. It mentions '13F periods' for context. It could note the required CIK, but the schema already does that. For a read-only tool with rich schema, it is nearly 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%, so the schema already describes both parameters (cik as SEC CIK, periods with min/max). The description adds only that periods 'include' trailing periods, which is a slight restatement. It does not add significant meaning beyond the schema, resulting in a baseline score.

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 gets an institution's position changes over recent 13F periods by CIK, specifying the resource (position changes) and the constraint (13F periods). This distinguishes it from siblings like get_institution_holdings (snapshot) and get_institution_position_changes (likely without period specificity).

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 when historical position changes over multiple quarters are needed, but it does not explicitly state when to use this tool over alternatives (e.g., get_institution_holdings for current holdings) or provide exclusions. Usage context is inferred but not guided.

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, which matches. Description adds pagination/sorting behavior but no additional safety notes, recency, or other constraints. Fair for a read tool.

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?

Single sentence, no extra words. All key elements present: verb, resource, identifier, features. 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 6 parameters, output schema, and annotations, the description adequately covers core purpose. Lacks error handling or edge cases, but sufficient for a retrieval tool with rich schema.

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 fully defined. Description mentions 'pagination' (implied by limit/offset) and 'sorting' but adds no semantics beyond the schema. 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?

Clearly states verb 'Get', resource 'PUT/CALL derivative positions', identifier 'by CIK (13F options)', and features 'pagination and sorting'. Distinguishes from siblings like get_institution_holdings by focusing on derivatives.

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?

No explicit when-to-use or when-not-to-use. Lacks comparisons to sibling tools or exclusions. Agent must infer that this is for options data from the context.

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

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

Annotations already declare readOnlyHint=true, and the description aligns by stating it 'gets' information. The description adds value by detailing the output content (name, AUM, holdings, filing history), which goes beyond the annotation. No behavioral 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 two sentences with no fluff. The purpose is front-loaded, and each sentence serves a distinct function: stating the action and providing usage guidance. Perfectly concise.

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 an output schema (not shown but flagged by context signals), the description need not enumerate return fields in detail. It still lists key output fields and explains the prerequisite. For a one-parameter lookup tool, this is mostly complete, though it could mention error handling for invalid CIKs.

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 describes the 'cik' parameter with a format example, and schema coverage is 100%. The description adds extra context ('Use get_institutions first to find the CIK'), which helps the agent understand how to obtain the parameter value. This adds meaning beyond the schema alone.

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: 'Get detailed information about a specific institutional investor by their SEC CIK number.' It specifies the verb ('get'), the resource ('detailed information about a specific institutional investor'), and the method ('by their SEC CIK number'). It also lists the returned fields (name, AUM, holdings, filing history), distinguishing it from siblings like get_institutions.

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 explicit when-to-use guidance: 'Use get_institutions first to find the CIK for an institution.' This helps the agent understand the prerequisite. However, it does not contrast with other institutional detail tools like get_institution_activity, but the context is sufficient for correct 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 provide readOnlyHint=true, so the agent knows it is a safe read operation. The description adds that it returns a list of filings with pagination. No contradictions or missing behavioral context that is not already covered by 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 front-loading the core purpose and key features. No extraneous text.

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 and the presence of annotations, input schema with 100% coverage, and an output schema, the description is sufficiently complete. It does not mention that 13F filings are quarterly, but that is not critical for selection.

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 adequate descriptions for all parameters. The description adds minimal value beyond that by mentioning pagination. 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 verb 'Get', the resource 'list of 13F filings', the key parameter 'by CIK', and the feature 'with pagination'. It distinguishes itself from siblings like get_institution_holdings or get_institution_activity by specifying it is for filings.

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?

No guidance is provided on when to use this tool versus its many siblings (e.g., get_institution_holdings, get_institution_activity). The agent would have no context to choose this tool over 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 indicate readOnlyHint=true, and the description aligns with that by stating it returns holdings details. It adds behavioral context beyond annotations by noting pagination support and the specific data returned (shares, value, weight).

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, no wasted words, and front-loaded with the key action and inputs. 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?

With an output schema present, the description does not need to detail return structures. It covers the core functionality, pagination, and what data is returned, making it sufficient for the 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?

Schema coverage is 100%, so the description does not need to re-explain parameters. It adds context about pagination and the nature of the returned data (latest 13F filing), but does not significantly enhance understanding beyond the schema definitions.

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 retrieves the full portfolio holdings for a specific institution by CIK, returning positions from the latest 13F filing with shares, value, and portfolio weight. It differentiates from sibling tools like get_institution_activity or get_institution_detail by focusing on portfolio holdings.

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 (e.g., when needing complete portfolio data for an institution by CIK). It does not explicitly state when not to use it or mention alternatives, but the use case is well-defined.

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, indicating a safe read operation. The description adds context about the output (sector allocation, top holdings) but does not elaborate on other behavioral traits like data freshness, pagination, or limits. It is consistent with annotations, but no additional behavioral details are provided.

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 concise sentence that front-loads the key action and resource. No extraneous words or redundant 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 presence of an output schema (as indicated by context signals), the description adequately covers the tool's purpose. It is a simple lookup with one parameter, so the description is sufficient. However, a slightly more detailed description of the analytics (e.g., typical fields returned) would be helpful but not necessary.

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

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

Schema coverage is 100%, and the description mentions 'by CIK', but the schema already defines the 'cik' parameter with a description. The description adds no meaningful semantic value beyond the schema, so baseline 3 applies.

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

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

The description clearly states the tool retrieves sector allocation and top holdings analytics for an institution's portfolio, identified by CIK. It uses a specific verb ('Get') and resource ('sector allocation and top holdings analytics'), distinguishing it from similar sibling tools like get_institution_holdings.

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 no guidance on when to use this tool versus alternatives. There are many sibling tools related to institutions (e.g., get_institution_holdings, get_institution_position_changes), but no scenarios, prerequisites, or exclusions 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=true, so description adds value by explaining the server-side computation and sorting behavior (by |changePercent| descending). No contradictions. Minor omission: no mention of what happens if no prior filing 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?

Two sentences: first defines purpose, second explains efficiency and sorting. Every sentence adds value; no fluff. Front-loaded with action verb.

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 that an output schema exists, the description sufficiently covers purpose, efficiency, and sorting. However, it could mention handling of missing prior filings or date boundaries. Still strong for a read-only tool with good annotations.

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 baseline is 3. The description adds context but does not elaborate on parameters beyond the example in cik description. It mentions sorting but not parameter constraints (limit/offset). Adequate but not exceptional.

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 ('Diff') and clearly identifies the resource (two quarterly 13F snapshots for an institution) and the output (per-position changes: new, increased, decreased, exited). It distinguishes this tool from siblings like get_institution_holdings.

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: for comparing latest filing to prior quarter. It also provides an alternative ('get_institution_holdings twice and diffing client-side') and explains why this tool is better (efficiency). Lacks explicit 'when not to use' but still 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, so the description correctly adds context about the data source (SEC 13F filings) and returned fields (shares held, portfolio weight, filing dates). No contradictions noted.

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 with no extraneous text. Purpose, data source, and output fields are front-loaded, making it efficient for an agent to parse.

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, data source, and key output fields. Given the presence of an output schema (not shown but referenced in context), it does not need to detail return values. Ample context 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% with full descriptions for each parameter. The description adds value by listing the output fields (shares held, etc.) but does not elaborate on parameter semantics beyond what the schema provides. Baseline 3 maintained.

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 'get', the resource 'institutional holders (13F filers)', and the scope 'for a company'. It distinguishes from sibling tools that focus on specific institutions (e.g., get_institution_detail) by specifying company-level query.

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 understanding institutional ownership concentration but does not explicitly state when to use this tool vs alternatives, nor does it mention when not to use it. No alternative tool names are referenced.

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 context beyond the readOnlyHint annotation by specifying that the tool returns two leaderboards with deduplication and volume metrics. It does not contradict the annotation and discloses the scope of the call.

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: the first defines the tool's purpose and output, the second provides an alternative. It is front-loaded and concise with 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 tool's simplicity (one optional parameter, no nested objects, output schema exists), the description fully covers the necessary context: what the tool returns, that it's market-wide, and the alternative for paginated results.

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 on the single 'limit' parameter, describing it fully. The description does not mention the parameter, but the schema already provides the necessary semantics. Hence, baseline score 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 it returns two specific leaderboards: 'topByAum' (largest holders by AUM, name-deduped) and 'mostActive' (highest 13F position-change volume). The verb 'get' and resource 'institution leaderboards' are clear, and the distinction from the sibling 'get_institution_top_aum' is provided.

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 notes that no CIK is required, simplifying use, and directs to 'get_institution_top_aum' for a full paginated AUM list, offering clear guidance on when to use an alternative. It lacks explicit 'when not to use' but provides sufficient context.

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

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

Annotations already declare readOnlyHint=true, so no additional safety disclosure needed. Description adds behavioral context: searches across all companies, ranks by AUM, optionally filters by minimum AUM. Does not mention pagination or return format, but output schema exists (not shown) to cover that.

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, well-structured. The first sentence fronts the core purpose and scope. The second sentence adds differentiation and optional feature. Very little redundancy, though could be slightly more concise.

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 simple tool with 3 optional parameters, readOnlyHint annotations, and output schema present, the description adequately covers key aspects (purpose, scope, differentiation, optional filter). Satisfies completeness for this level of complexity.

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% (all three parameters documented). The description adds a brief mention of minimum AUM but no additional semantic value beyond what the schema already provides. 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?

Clearly states 'Discover top institutional holders across the entire company universe ranked by assets under management (AUM)' with a specific verb and resource. Explicitly distinguishes from sibling tool get_ownership by noting the scope difference (across all companies vs. single company).

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 context for when to use this tool compared to get_ownership (single company vs. all companies). Mentions optional parameter (minimum AUM) and practical use case ('identifying smart money flows'). Lacks explicit when-not-to-use statements but sufficiently guides 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 indicate readOnlyHint=true. The description adds behavioral details: extended-hours inclusion with resolution constraints, which is valuable beyond the schema. 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?

Three well-structured sentences with no fluff. Key information is front-loaded: what it returns, resolutions, usage, and extended-hours details. 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?

With annotations covering safety (readOnly) and output schema presumably detailing return fields, the description covers usage context, resolution options, and extended-hours behavior fully.

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% (all parameters described). The description adds nuance: 'Set extended=true (1-minute resolution only) to include premarket...'—this clarifies a constraint not fully captured in schema descriptions.

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 intraday OHLCV candles at specific resolutions (1, 5, 15, 30, 60 min). This distinguishes it from sibling tools like 'get_historical_prices' which likely provide daily or longer-term 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 recommends using this tool for 'intraday price action analysis, volume patterns, and short-term technical analysis'. It does not explicitly mention when not to use or alternatives, but the context is clear given 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. The description adds significant behavioral context: empty calendar is normal, vote windows are predictions with provenance/granularity, affectedTickers are verified verbatim, and sponsorTradeFacts require citing both dates with no suggestion of wrongdoing.

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 long but well-structured with front-loaded core purpose and subsequent details. Every sentence provides useful information, though it could be slightly more concise without losing 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?

Given the complexity (5 parameters, output schema exists), the description covers behavior, edge cases, warnings, and interpretation thoroughly. It is complete for an AI 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 3. The description adds value by stating defaults for from/to and minRelevance, and explains the 'none' option for minRelevance as 'explicit opt-in to the full audit trail'.

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 returns a 'Forward-looking legislative catalyst calendar' of upcoming House/Senate floor votes filtered to market-relevant items. This specific verb-resource combination distinguishes it from sibling tools like get_economic_calendar or get_earnings_calendar.

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 defaults (from=today, to=+14 days, minRelevance=low) and how to interpret an empty result (normal state, not error). It does not explicitly state when to use this vs. alternatives like get_policy_events, but the context is clear enough for an AI agent.

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 read-only nature is known. The description adds detail on output metrics but no additional 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?

Extremely concise: two sentences front-load the purpose and use case with 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?

Tool is simple (one optional parameter with enum) and the description fully explains output and usage. Output schema exists, so return value details are 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?

Schema coverage is 100%; the description merely reiterates the universe parameter without adding new meaning beyond the schema's enum values and default.

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 verb 'Get' and resource 'market breadth aggregates', listing specific metrics. However, it does not explicitly differentiate from sibling tools like get_market_metrics, so it lacks sibling distinction.

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: 'add market-state context to commentary, tweets, or daily summaries.' It does not, however, state when not to use or name 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, so the description's burden is lower. The description adds behavioral context by listing the computed metrics returned (volume averages, volatility, SMAs, trend direction), which is consistent with the read-only nature. 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 two sentences, front-loaded with the tool's action and output, and every sentence adds value. No redundant or missing 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 has a single required parameter (with clear schema), an output schema (not shown but flagged true), and clear sibling differentiation, the description is complete. It covers purpose, usage context, and expected outputs.

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