market-data

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

With no annotations provided, the description carries the full burden of disclosure. It discloses output type (score, worst windows, findings), states it does not return corrected values, and notes it is free. While it doesn't cover side effects or permissions, its read-only audit nature is reasonably transparent.

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

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

The description is two sentences, front-loaded with the core purpose and includes an explicit alternative. Every word earns its place with 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?

There is no output schema, but the description summarizes the result types (score, worst windows, findings) and explicitly states what is not returned. For a moderate-complexity tool with three parameters and a nested object, this provides sufficient context for an agent to select and invoke the tool correctly.

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

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

Schema description coverage is only 33% (only bars has a description). The tool description implies symbol and timeframe but does not explain their formats or constraints. The bars description in the schema clarifies the columnar structure, but overall parameter semantics are only partially supplemented. A score of 3 reflects the minimum viable compensation.

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 audits user-submitted OHLCV bars against a verified archive and returns an accuracy verdict. It explicitly differentiates from get_bars by noting it does not provide corrected values. This distinguishes it from sibling tools.

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

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

The description explicitly names get_bars as the alternative for corrected values, implying this tool should be used to identify inaccuracies while get_bars should be used to obtain correct data. This provides clear when-to-use and when-not-to-use 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?

No annotations are provided, so the description must fully disclose behavior. It states it returns a signed URL and lists pricing, but it is ambiguous whether calling this tool initiates a purchase, simply generates a URL for later use, or returns a price quote. The phrase 'Priced as the SKU' is vague. There is no mention of side effects, permissions, or whether the action is read-only or transactional.

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

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

The description is a single dense sentence packed with pricing and pack details. It is efficient in information density but poorly structured, using inline slashes and parentheses that make it hard to scan. A bulleted list or clearer separation of pack options would improve readability without losing conciseness.

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

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

For a tool with multiple pack types and conditional parameters, the description covers pack selection thoroughly, including pricing and required parameters. However, it lacks an explanation of what a 'signed URL' entails (e.g., access vs. payment) and whether the tool has side effects. With no output schema and no annotations, this ambiguity leaves a notable gap in completeness.

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

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

The schema already provides enum values and some descriptions (67% coverage). The description adds significant semantic value by explaining what each pack contains (e.g., 'everything ($149: both packs + all token sequences, $730 list)', 'features (feature matrix, crypto $7 / equity $4)') and clarifies conditional parameter requirements (e.g., symbol required for specific packs, tf constraints for features). This goes beyond the schema's raw parameter 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 produces a 'Signed URL for a dataset SKU', which conveys the overall function of generating a signed URL for a data bundle. The pack list distinguishes it from sibling data-access tools like get_bars or get_features, as it focuses on building bundles/packages. However, the verb is implicit ('Signed URL' is a noun phrase), so it's not perfectly 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 provides detailed guidance on which pack to select based on desired data, including price breakdowns and specific conditions (e.g., 'mtf... crypto only', 'symbol required for tokens|dataset|mtf|features', and 'tf features only... crypto: 1h or 15m; equity: 1d'). This effectively tells the user when to use each option, but does not explicitly mention alternatives or exclusions relative to 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?

No annotations are provided, and the description does not disclose behavior beyond the vague 'Free discovery'. It doesn't explicitly state read-only/safe usage, return format, or any constraints. The term 'free' is ambiguous (cost vs. unrestricted).

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, front-loaded with a clear label, no redundancy. The colon-separated list efficiently enumerates the catalog dimensions.

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

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

For a zero-parameter tool, the description covers the core aspects of the catalog but leaves ambiguity about 'pricing' and the exact nature of the output. Without an output schema, it should ideally state what the agent will receive (e.g., a list of available symbols/timeframes). Still, it's adequate for a basic discovery tool.

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

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

The tool has no parameters, so the description has no parameter semantics to add. Schema coverage is 100% (empty object), and baseline for 0 params is 4.

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

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

The description identifies the tool's scope (symbols, timeframes, ranges, pricing, quality legend) and distinguishes it from data retrieval siblings by focusing on catalog metadata. However, 'Free discovery' as a verb phrase is vague; a more explicit verb like 'Lists available' would clarify.

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 on when to use this tool vs alternatives. It does not explicitly state that this is a starting point for exploring available data before querying specific tools, nor does it name any sibling tools as 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?

With no annotations, the description must carry behavioral disclosure. It notes two traits: candles are 'quality-flagged' and 'priced per 1,000 candles,' which gives some sense of quality processing and cost. However, it omits any mention of authentication, rate limits, data range behavior, or return structure, leaving critical unknowns.

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, using two short fragments that front-load the core output ('Quality-flagged OHLCV candles') and then the cost note. Every phrase adds some information, though it remains under-specified.

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

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

For a tool with four parameters, no output schema, and zero annotations, this description is far from complete. It does not explain parameter interactions, return fields, pagination, or any typical usage context, leaving the agent to rely on assumptions.

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 has 0% description coverage for its four parameters, and the description adds no parameter-specific meaning. An agent cannot infer what 'symbol', 'tf', 'start', or 'end' require regarding format, defaults, or constraints from either source.

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 identifies the resource as 'OHLCV candles' with a 'quality-flagged' qualifier, which conveys the tool's primary output. However, it lacks a verb (e.g., 'retrieves' or 'returns') and does not explicitly distinguish get_bars from sibling data tools beyond the acronym.

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 over alternatives. There is no mention of contexts, exclusions, or comparisons to sibling tools like get_fundamentals or get_orderflow.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It only enumerates series names and says nothing about read-only behavior, return format, effects of start/end parameters, or any other operational characteristics. The tool's behavior is completely opaque.

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 short, but this is under-specification rather than conciseness. It is a fragment with no structure or explanation, sacrificing essential information for brevity.

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 3 parameters, no annotations, no output schema, and only a bare list of series, the tool is severely underdocumented. An agent would have no idea what the tool does, how to use its parameters, or what to expect as a response. This is far below a minimally viable description.

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 has 0% description coverage, so the description must compensate. It minimally helps by listing likely valid values for the 'series' parameter, but it never explicitly ties the list to that parameter. The 'start' and 'end' parameters are left entirely unexplained, leaving a significant semantic gap.

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

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

The description is a noun phrase: 'Context series: fear_greed_1d, VIX_1d, DXY_1d, TNX_1d, DJI_1d.' It lacks a verb and never states what the tool actually does with these series. While it lists specific series identifiers, the function remains ambiguous—it could be retrieving, defining, or listing them. This is slightly more than a tautology but far from a clear purpose statement.

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 sibling tools like get_market_pulse or get_bars. There is no mention of use cases, prerequisites, or context in which this tool is appropriate. The description offers zero direction for tool 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?

With no annotations, the description must disclose behavior. It only says 'curated' and lists event types; it does not mention whether operations are read-only, how results are returned, or any limitations such as rate limits or data coverage.

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

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

A single, dense sentence effectively communicates the tool's core function without redundancy, earning top marks for conciseness.

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 lack of output schema and annotations, the description is underspecified. It does not state the response structure, whether events include timestamps or metadata, or how the type parameter affects the results, leaving an agent with insufficient information to invoke the tool confidently.

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

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

The schema provides no descriptions for start, end, and type. The description's mention of 'in a range' and the listed event types loosely correlates with start/end and type, but it does not explain parameter formats, required vs optional, or accepted values.

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 providing curated macro/crypto events, listing specific event types (FOMC, halvings, incidents), which distinguishes it from sibling data tools. Though it lacks an explicit verb like 'get' or 'list,' the resource and scope are evident.

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 alternatives like get_bars or get_fundamentals. The phrase 'in a range' implies a temporal scope, but there are no exclusion criteria or use-case 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It mentions 'leakage-safe' and 'priced per call,' which are useful traits, but it never describes the actual operation, return format, or any edge cases. The disclosure is too thin.

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?

At 9 words, the description is brief, but the brevity is under-specification, not effective conciseness. The first sentence is an incomplete fragment, and the second sentence on pricing adds little structural value. It is too short to be useful.

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 4 undocumented parameters, no annotations, and no output schema, the description is far too thin. It hints at leakage safety and pricing but omits core information about required inputs and the matrix structure, making it inadequate for an agent to invoke correctly.

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

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

The schema has 4 parameters (symbol, tf, start, end) with 0% description coverage. The description does not explain any of these parameters or how they relate to the feature matrix. It completely fails to compensate for the schema's lack of documentation.

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 is a noun phrase ('Documented leakage-safe feature matrix rows') with no explicit verb, so it doesn't clearly state the action. It distinguishes from siblings by referencing feature matrix rows, but relies on the tool name to imply retrieval. This is a moderate clarity level.

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

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

There is no guidance about when to use this tool versus sibling tools like get_bars or get_fundamentals. The only additional statement, 'Priced per call,' is a cost note, not usage guidance. It offers no timing, prerequisites, or alternative recommendations.

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?

With no annotations, the description carries the full burden and does well by disclosing point-in-time semantics, inclusion of delisted filers, and that restatement vintages are returned with filed dates. It does not cover return structure or edge cases, but the core behavioral traits are clearly communicated.

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 tight sentences, front-loaded with the tool's purpose and key differentiators. Every phrase adds value without redundancy or filler.

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

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

Despite having no output schema and 5 parameters, the description covers the core functionality, scope, and two key parameters. It lacks explicit return-value details and start/end semantics, but for a read-oriented fundamentals tool, it is reasonably complete.

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

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

Schema description coverage is 0%, so the description must compensate. It explicitly explains 'as_of' and 'concept', but leaves 'start', 'end', and 'symbol' undocumented. Symbol is obvious from the required field, but start/end date parameters are not explained, leaving a notable gap.

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

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

The description clearly states a specific verb+resource: it retrieves point-in-time SEC XBRL fundamentals. It further distinguishes the tool by mentioning the 80-filer universe, delisted companies, and restatement vintages with filed dates, which separates it from sibling tools focused on bars, events, and funding.

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

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

The description gives clear usage context: 'Pass as_of for what was knowable then' and 'Filter by concept' provide specific how-to guidance. However, it does not explicitly discuss when not to use this tool or name alternative tools, so it falls shy of a 5.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the 'checksummed archive' indicating data integrity, but does not disclose response format, pagination, ordering, rate limits, or any mutation behavior.

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

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

A single sentence that is direct and front-loads the core purpose, with the archive trait as a parenthetical. Every word adds value with no fluff, making it appropriately 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?

With no annotations and no output schema, the description needs to explain behavior and return values fully. It gives a high-level overview but omits parameter semantics, default behaviors, and output details, making it insufficient for a 3-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 description coverage is 0%, and the description does not mention any of the parameters (symbol, start, end). It fails to compensate for the missing schema documentation, leaving parameter meaning and format ambiguous.

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 resource as 'Perp funding-rate settlement history' and adds specificity with 'from listing date' and 'checksummed archive'. It distinguishes from sibling tools like get_funding_spread by focusing on settlement history, but lacks an explicit verb like 'retrieves'.

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 given on when to use this tool versus alternatives such as get_funding_spread or get_bars. The context of 'from listing date' provides some scope, but there are no explicit use cases, prerequisites, 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?

With no annotations, the description carries the burden of disclosing behavior. It adds useful context: hourly cadence, 67 symbols, Hyperliquid vs Binance 1h-equivalent normalization, and the start date from HL genesis. However, it does not describe return format, error behavior, or limitations beyond the symbol count.

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, front-loaded sentence with dense, relevant information: data product, symbol count, sources, cadence, and start date. Every element contributes value with no redundant wording.

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

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

While the description provides useful data context, it leaves significant gaps for a tool with no annotations, no output schema, and undocumented parameters. The agent would not know how to construct valid requests or interpret the response, reducing completeness for reliable invocation.

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

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

Schema description coverage is 0% and the description does not explain the meaning or format of symbol, start, or end. It mentions '67 symbols' but does not specify how to select one, nor does it define date formats. The description fails to compensate for the lack of 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 identifies the resource: hourly CEX-vs-DEX funding spread for 67 symbols comparing Hyperliquid and Binance funding. It distinguishes itself from sibling tools like get_funding by specifying the spread calculation and data scope, though it lacks an explicit action verb beyond the tool's name.

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 alternatives such as get_funding or get_bars. It implies usage by describing the data, but does not state conditions, exclusions, or preferred 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?

With no annotations, the description is the only source of behavioral context. It discloses that data is 'as filed' and limited to 80 symbols since 2016, but does not explain how start/end date parameters affect results, response format, or update frequency. This is a moderate level of disclosure.

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, information-dense sentence that front-loads the core purpose and concisely includes scope, time range, and data fields. Every word adds value without unnecessary elaboration.

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

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

The tool has no annotations or output schema, so the description must provide comprehensive context. It gives a high-level overview but omits parameter semantics, usage conditions, and return structure. This leaves a significant gap for an agent to correctly invoke and interpret the tool's output.

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

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

Schema description coverage is 0%, and the description does not explain any of the three parameters (symbol, start, end). Symbol is required but its format is not mentioned; start/end are present but completely unexplained. The description fails to compensate for the lack of schema documentation.

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 SEC Form 4 insider transactions, specifying the data scope (80 symbols, since 2016) and content (officer/director trades, shares, price, post-trade holdings). This distinguishes it from sibling tools like get_institutional and get_fundamentals.

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 insider transaction data but provides no explicit guidance on when to use this tool over siblings or when not to use it. Alternatives like get_institutional are not mentioned, leaving the agent to infer from the tool name and data type.

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?

No annotations are provided, so the description carries the full burden. It adds transparency by disclosing the data source (SEC DERA structured tables) and a scope limitation (81 symbols), but it does not mention behavior like error handling, range constraints, or whether only the 81 symbols are supported.

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-loaded with the core purpose and output components. It uses a colon to list what is included, achieving maximum clarity in minimal 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?

For a tool with three parameters and no output schema, the description adequately lists the output content but leaves gaps: it does not explain the 81-symbol limitation, parameter formats, or the meaning of start/end. Some important context for successful invocation 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 0% and the description does not mention any of the three parameters (end, start, symbol). It provides no additional meaning beyond the schema, such as symbol being required or date format expectations.

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 quarterly 13F institutional aggregates including holders, shares, value, and QoQ deltas, sourced from SEC DERA tables. This specific verb and resource set distinguishes it from siblings like get_insider and get_fundamentals.

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 when institutional 13F holdings data is needed, with clear context about the quarterly cadence and QoQ changes. It does not name alternatives or exclusions, but the domain is distinct enough that the intended use is evident.

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?

With no annotations, the description carries the full burden. It discloses a key limitation: 'One day of values' and notes that 'history behind each number is the priced product', which tells the agent the scope and potential paywall. However, it does not explicitly mention read-only nature, auth requirements, or rate limits, leaving some gaps.

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 concise sentences that pack meaningful information: what the tool returns, the scope, and a pricing/limitation note. No wasted words; it is front-loaded with the most important phrase 'FREE daily pulse across the catalog'.

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 there is no output schema and zero parameters, the description should fully explain return values. It names content areas (regime flips, funding extremes, CEX-vs-DEX spread extremes, biggest daily moves) but does not specify the exact structure or field names. Still, for a snapshot summary tool, it provides reasonable guidance. The note about history being the priced product adds context for expectations.

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

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

The tool has zero parameters, and the schema is empty. The description adds semantic context by listing the types of values returned (regime flips, funding extremes, etc.), which helps the agent understand what the output represents even though there is no parameter to document.

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

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

The description clearly states the tool provides a 'daily pulse across the catalog' with specific components like 'regime flips' and 'funding extremes'. It differentiates from sibling tools (e.g., get_regime_label, get_funding_spread) by covering the whole catalog as a combined snapshot, though it doesn't explicitly name alternatives.

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

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

Usage context is implied via 'across the catalog' and the mention of 'one day of values', suggesting it's for a broad market overview rather than deep dives. However, there is no explicit 'when to use' or 'when not to use' guidance, nor references to alternative tools.

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

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

The description adds useful context about per-row quality flags and data provenance (verified archive vs. flagged bridge), which goes beyond the bare name. However, with no annotations, it does not disclose other behavioral aspects like time range handling, pagination, or potential errors, leaving significant gaps.

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, efficient sentence that front-loads the core resource and adds a key differentiator. Every word adds value, with no redundant or filler content.

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

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

For a tool with 3 parameters and no output schema or annotations, the description is minimal. It does not explain parameter formats, return structure beyond quality flags, or usage context, leaving the agent ill-equipped to use the tool correctly without additional assumptions.

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 0%, and the description provides no information about the parameters (symbol, start, end). The agent must rely entirely on the parameter names and schema structure, which is insufficient for correct invocation.

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 resource (open interest), the frequency (hourly), and a distinctive feature (per-row quality flags). This differentiates it from sibling tools like get_bars or get_funding, even without an explicit verb, which is supplied by the tool name.

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 alternatives, nor any exclusions or prerequisites. The description only states what data is returned, leaving the agent to infer appropriate 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?

With no annotations provided, the description carries the full burden for behavioral context. It usefully explains metric semantics (buy_ratio 0.5 = balanced) and data availability differences (1h/1d via API, denser tiers in packs), adding value beyond the schema. It does not mention output format, but the listed metrics and buy_ratio hint at the response contents.

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

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

The description is short and packs multiple pieces of information into a single sentence. However, the phrase 'denser tiers in packs' is ambiguous and could be clearer, so it is not 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?

The tool has 4 parameters, no output schema, and no annotations, so the description must supply substantial context. It covers core metrics and timeframe availability but omits response shape, parameter formats, and use cases, leaving the description incomplete for reliable invocation.

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

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

Schema description coverage is 0%, and the description does little to compensate. It only hints at timeframe options via '1h/1d' and does not explain start, end, or symbol requirements. The schema itself has bare parameter names and an enum, but the description adds minimal meaning beyond that.

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's output as taker buy/sell imbalance, trade counts, and quote volume, which distinguishes it from sibling data tools like get_bars or get_open_interest. Although no explicit verb is used, the tool name 'get_orderflow' plus the listed metrics convey its purpose well.

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

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

There is no explicit guidance on when to use this tool versus alternatives like get_bars or get_open_interest. The description implies it is for order flow metrics but does not state scenarios, exclusions, or why an agent would choose it over a sibling 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?

With no annotations, the description carries the burden of disclosure. It explicitly reveals that the tool is free and public, shows the last 30 audits, and includes failures rather than hiding them. It does not discuss rate limits or output format, but for a simple zero-parameter getter, this is adequate transparency.

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

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

A single sentence delivers a wealth of specific information: public/free, time window (last 30 days), frequency (daily), audit dimensions, and failure visibility. Every clause adds value with 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?

For a zero-parameter tool with no output schema, the description is remarkably complete. It tells the agent exactly what the tool returns (a scoreboard of audit results), the scope (last 30 daily audits), the audit categories, and that failures are included, which fully covers the expected behavior.

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

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

The tool has zero parameters, so there is no parameter semantics to explain. The baseline score of 4 is appropriate since the description correctly implies there are no configurable inputs.

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

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

The description clearly states the tool provides a public scoreboard of the last 30 daily fresh-data audits, listing specific audit dimensions (cross-venue vs Coinbase, rebuild exactness, depth sanity) and notes failures are included. This distinguishes it from sibling data-retrieval and validation tools.

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

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

The description makes it clear this is the tool to get recent audit results, and 'FREE public' implies no authentication barrier. However, it does not explicitly name alternative tools (e.g., audit_my_data) or state when not to use this, so usage context is clear but exclusions are absent.

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?

With no annotations, the description carries the full burden. It discloses that the label is descriptive, based on the most recent completed bar (avoiding look-ahead), and explicitly non-predictive. It does not cover return format or potential errors, but the key behavioral traits are communicated.

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, information-dense sentence. It front-loads the core output (market-state label), immediately qualifies the timeframe and non-predictive nature, and contains no unnecessary 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?

For a simple two-parameter read-only tool with no output schema, the description covers the essential selecting criteria: what it returns, the timing basis, and the non-prediction caveat. It lacks explicit parameter definitions and label value examples, but the overall context is sufficient for an agent to invoke it 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 description coverage is 0%, so the description must compensate. It mentions 'timestamp' in the context of 'at or before a timestamp', clarifying its use, but does not explain 'symbol' at all. The agent must infer that 'symbol' refers to the market instrument, which is a gap.

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

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

The description clearly states the tool returns a descriptive market-state label for a specific bar, with the quadrant scheme (trend/range × calm/vol) explicitly defined. It distinguishes itself from similar tools like get_market_pulse by focusing on a label for the most recent completed bar, and the 'Not a prediction' caveat adds precision.

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 by specifying the tool works for the most recent completed bar at or before a timestamp, and the 'Not a prediction' statement acts as an exclusion. However, it does not explicitly name alternative tools or provide when-not-to-use guidance beyond the prediction caveat.

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?

With no annotations, the description carries the transparency burden. It explains the output content (windows, symbols, freshness) but does not explicitly state whether it is safe, read-only, or requires authentication. The 'FREE:' hint adds some behavioral context about cost.

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, compact sentence that front-loads the key feature ('FREE') and clearly specifies the returned information. Every word adds value without unnecessary verbosity.

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 parameterless tool, the description sufficiently explains the return values (extended windows, new symbols, freshness). No output schema exists, so the description must cover what is returned; it does so adequately, though the term 'sections' could be more precise.

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

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

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameter meanings because there are none; it focuses purely on the return value.

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

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

The description clearly states the tool returns what the daily refresh changed, with specific details like extended dataset windows, new symbols/sections, and freshness per asset class. It distinguishes itself from sibling tools like get_bars or get_events by focusing on refresh changes.

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 'FREE:' indicating no cost, providing contextual guidance on when to use it. It clearly defines the scope (daily refresh changes), but does not explicitly name alternatives or state when not to use it.

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

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

No annotations are provided, so the description must carry the full burden. It does explain the detection logic (impossible fills outside bar's traded range, pins at extremes), but it does not explicitly state whether the tool is read-only, has side effects, or how results are returned. This leaves some ambiguity about the tool's safety and behavior.

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, efficient sentence that front-loads the key action and includes specific detection criteria. The word 'FREE' is mildly extraneous but not wasteful. Overall, 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?

The description covers the core purpose and provides some behavioral details, but it lacks information about the return format of the verdict, example usage, or how this tool relates to sibling validation tools. Given no output schema and no parameter descriptions, more context would be needed for full completeness.

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

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

The schema has zero parameter descriptions, so the description must compensate. It partially explains the 'signals' parameter structure (t, price) but omits the 'side' field and does not explain 'symbol' or 'tf'. This leaves most parameters underspecified.

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: submitting backtest signals and receiving an execution-feasibility verdict. It also distinguishes itself from siblings like survivorship_check and validate_backtest_data by specifically detecting lookahead bias (impossible fills outside bar range, fills at extremes).

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 one has backtest signals and wants to check execution feasibility. However, it does not explicitly state when to use this tool versus alternatives like validate_backtest_data or audit_my_data, nor does it mention any exclusions or 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?

With no annotations provided, the description carries the full burden. It discloses some behavioral aspects: it compares the submitted universe against covered delisted symbols and reports which symbols died. However, it omits details like whether it is read-only, how 'died' is determined, or any edge cases. The description adds value but is not comprehensive.

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, information-dense sentence. It front-loads the key selling point ('FREE') and then immediately states the action and result. Every word earns its place, with no fluff or repetition.

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 lack of annotations and output schema, the description does a fair job explaining the core functionality and output (verdict and lists). However, it does not cover all parameters (asset) or provide details about the response structure, error conditions, or prerequisites. It is complete enough for a simple tool but has clear 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 description coverage is 0%, so the description must compensate for parameter meaning. It maps 'universe' to symbols and 'window' to start/end, but it does not explain the 'asset' parameter, date formats, or optionality. The description provides only partial semantics, leaving the agent guessing on key details like asset type and date range syntax.

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 ('submit') and resource ('backtest universe + window') and clearly states the output ('survivorship-bias verdict'). It distinguishes itself from sibling tools like lookahead_check and audit_my_data by focusing on delisted symbols, making the tool's purpose unambiguous.

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

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

The description clearly implies when to use the tool: when you want to check for survivorship bias in a backtest universe. It does not explicitly mention alternatives or when not to use, but the scenario is clear. Sibling tools exist, but no exclusion is provided, so it earns a 4 rather than 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?

No annotations exist, so the description carries the full burden. It discloses that the tool produces a report and implies it is a pre-flight check, but it does not explicitly state side effects (e.g., read-only, no data modification) or any rate limits/requirements. This is adequate but not rich.

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, front-loaded sentence that conveys purpose and output content without fluff. Every element earns its place.

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

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

The description explains the high-level output categories and usage timing, which is helpful. However, with no output schema and minimal parameter information, the description is incomplete for an agent to safely and correctly invoke the tool across all contexts.

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 0%, and the description does not compensate. It refers to a 'dataset spec' but never explains individual parameters (symbol, tf, start, end) or their formats. An agent cannot infer how to correctly populate the parameters from the 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 produces a 'Quality report for a dataset spec before you backtest on it' and enumerates report contents (coverage, per-bar quality distribution, gaps, warnings). This is specific and action-oriented, but it does not explicitly distinguish itself from siblings like audit_my_data or get_quality_receipts.

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 phrase 'before you backtest on it' provides clear context for when to use the tool. However, it does not mention alternatives or exclusions, such as when to choose a different validation tool like lookahead_check or survivorship_check.

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