XOOMAR market data

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

With no annotations, the description carries the full disclosure burden, and it does state the concrete content returned: endpoints, parameters, rate limits, CSV downloads, and attribution terms. This tells an agent what to expect beyond a vague 'reference.' It doesn't mention return format (text vs structured) or whether it is read-only, so it stops short of full 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?

Two tight sentences: the first front-loads the content inventory, the second gives the usage condition. No filler, no repetition of the name or title, and the most decision-relevant information (when to call it) is easy to locate.

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 parameterless documentation tool with no output schema, the description is sufficient: it says what content is available and when to reach for it. Slightly more detail on response shape would make it fully self-contained, but 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?

The tool takes zero parameters, so there is no parameter semantics to document and the baseline is 4. No schema detail is required or missing.

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 names a specific resource — the underlying free API — and enumerates what it covers: endpoints, parameters, rate limits, CSV downloads, and attribution terms. This clearly distinguishes it from the sibling data-query tools, which return market data rather than API documentation. It lacks a crisp verb+resource formulation but the purpose is unambiguous.

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

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

It gives explicit routing guidance: 'Use when a tool here does not cover the exact query,' which positions it as the fallback for the 21 sibling data tools. The condition is precise and actionable, though no counter-examples or exclusions (e.g. don't use this when a data tool already fits) are spelled out.

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 usefully discloses provenance (company-filed XBRL, not market data) and timing semantics ('as of the filing period'), signaling reporting lag. It says nothing about universe size, refresh cadence, or whether it is a snapshot vs historical series.

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, front-loaded sentence with no filler, and the provenance qualifier is the most useful piece of information placed inline. It is terse, though for a whole-dataset tool a little more specificity would not be waste.

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?

No annotations, no output schema, and no parameters means the description is the only contract, and it stops at naming measures. It does not indicate the shape of the result (per-company rows? single aggregate?), coverage, or time span, which an agent needs to use it 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?

Zero parameters, so the baseline is 4. The description compensates somewhat by enumerating the returned measures (coins, fair value, cost basis), which is the closest thing to a field contract in the absence of an output 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?

States the specific resource (Bitcoin holdings of public companies) and even the provenance (their own XBRL filings), plus the fields exposed (coins, fair value, cost basis). It is distinguishable from crypto_market and company_financials, though it never names a sibling to sharpen the boundary.

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 when-to-use guidance, no prerequisites, and no alternative named. The only contextual hint is 'as of the filing period', which implies the data is periodic rather than real-time, but that is inference, not 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?

With no annotations provided, the description carries the full burden of behavioral transparency. It adds useful context by noting that the fourth quarter is derived from the annual report, that figures are from the company's own XBRL filings, and that balance sheet values are 'instants'. However, it does not disclose limitations such as data coverage depth, currency, units, or potential missing periods.

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 with no filler words; every clause contributes specific metric or source information. It is front-loaded with the most prominent quarterly metrics. The long list format is slightly unwieldy, especially at the end, but it remains concise for the amount of information conveyed.

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 a single parameter and no output schema, the description does a good job of telling the agent what data will be returned: quarterly and annual income statement metrics, cash flow items, capital returns, and balance sheet instants. It also explains a subtle derivation rule for Q4. Minor gaps include exactly how far back data goes and whether values are in millions or as reported, but the core calling context is 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 100%, and the schema already explains the symbol parameter with examples and the class-share convention like BRK-B. The tool description adds no additional parameter semantics beyond what the schema provides. The baseline of 3 applies because the schema fully documents the only parameter.

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

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

The description clearly identifies the resource—company financials from SEC XBRL filings—and enumerates the specific metrics returned. It distinguishes itself from sibling market-data tools by focusing on company-reported financial statements. However, it lacks an explicit operative verb like 'returns' or 'retrieves', relying on the title and list format.

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 this tool is for fundamental company financials by listing revenue, EPS, cash flow, buybacks, and balance sheet items. It does not name any sibling tools or state when to prefer this over alternatives such as earnings_calendar or macro_series. There is no explicit exclusion or 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?

With no annotations provided, the description carries the full burden. It only states what is returned (8-K reports with item numbers) but does not disclose read-only nature, rate limits, pagination, or any side effects. It also doesn't mention authentication or data freshness. Minimal behavioral disclosure beyond the basic function.

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, tightly written sentence. It front-loads the primary purpose and includes illustrative examples without extraneous words. Every element earns its place, making it highly efficient.

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

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

The tool has 3 optional parameters and no output schema. The description explains what it returns (reports with item numbers) and mentions the two usage modes (ticker or latest), but it omits the 'days' parameter's role and any hint about the return structure. Given no output schema, some description of expected output fields or pagination would improve completeness.

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

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

Schema description coverage is 67% (days lacks a description). The description adds meaning to item (examples: 2.02 earnings, 5.02 officer changes) and ticker (implicitly tied to 'for a ticker'), but does not explain the 'days' parameter at all. Since coverage is not high, the description partially compensates but leaves days undefined.

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 (8-K current reports) and the specific aspect (item numbers like 2.02, 5.02). It distinguishes from siblings by focusing on 8-K filings with item numbers and supports filtering by ticker or latest across companies. The verb 'current reports' implies retrieval, making the purpose unambiguous.

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

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

The description provides usage context: 'for a ticker or the latest across companies' indicates when each mode applies. However, it does not explicitly exclude alternatives or mention when not to use this tool compared to siblings like earnings_calendar or company_financials. The guidance is implied rather than explicit.

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 the full burden of behavioral disclosure. It does reveal the weekly frequency, the two query modes, and the output fields, but it omits any mention of pagination, date ranges, or market coverage limitations, leaving some behavioral aspects unclear.

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 entire description is a single well-structured sentence with parenthetical examples that compress important parameter guidance. It is front-loaded with the core function 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?

The description covers the core return fields and the two invocation modes, which is good for a simple data-fetch tool. However, without an output schema and without clarifying the 'limit' parameter, some ambiguity remains for an agent attempting to call the tool correctly in all cases.

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 market parameter gains meaning through example slugs and the 'omit for the latest report' note, but the limit parameter is left undocumented in both schema and description. Since schema coverage is exactly 50% and the description partially compensates, the score is mid-range.

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

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

The description clearly identifies the tool as a weekly CFTC Commitments of Traders data source, specifies two call modes (latest across markets vs. historical for one market), and names the fields returned (open interest, long/short by trader category). It is easily distinguished from sibling tools by the unique resource and 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?

The description implies usage for CFTC positioning needs with examples of market slugs, but it never explicitly states when to prefer this tool over sibling tools or provides exclusion criteria. Agents must infer the use case from domain keywords rather than receiving explicit 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?

With no annotations, the description carries the full behavioral burden. It does add scope constraints beyond the schema: 'history' suggests time-series, 'recent' suggests a time window, and options are limited to BTC or ETH. However, it does not disclose side effects, rate limits, authentication needs, or response behavior. For a read-only data tool this is adequate but 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, well-organized sentence that lists four datasets with their key qualifiers. It is front-loaded with the primary mode (open interest) and avoids fluff. It could lead with a clearer subject-verb construction, but it is compact and informative.

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 multi-mode tool with two parameters and no output schema, the description covers each dataset mode and the relevant slug constraints. It does not explain the output format or clarify whether slug is needed for liquidations, but for invocation purposes the agent can correctly select dataset and provide slug where relevant. The main gaps are behavioral details rather than invocation essentials.

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 50% (slug is described, dataset is not), but the description compensates by explaining what the dataset enum means for each mode and how slug should be used (e.g., 'open-interest: symbol slug', 'options: BTC or ETH', 'whales: coin'). It maps slug requirements per dataset, though it does not explicitly state that liquidations ignore slug.

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 names four distinct crypto datasets (open interest, liquidations, options metrics, whale positions) and clearly states what each delivers. It lacks a single explicit verb like 'retrieves' and the title is generic, but the resource and scope are identifiable. It is distinguishable from sibling tools because it is crypto-specific and names exchanges/venues like Deribit and Hyperliquid.

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 alternative-routing guidance is given, but the dataset list implies the tool is for these specific crypto data needs. There is no mention of when not to use it or what to use instead. The context of sibling tools (equities, rates, etc.) makes the crypto scope clear, but the description itself does not state selection criteria.

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 fully discloses behavior: source (8-K filings), estimation logic (last year's date plus 52 weeks, with basis), default window (today to 14 days), max window (120 days), status filter, and that it returns dates only. This is unusually rich for a description and covers all key behavioral aspects.

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

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

Three sentences, each dense with information, with the core purpose front-loaded. No filler 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?

The description covers the two modes, date windows, status, and output scope ('Dates only'), which is sufficient for an agent to invoke correctly. The exact return format (array vs objects) is not specified, but the statement 'Dates only' gives adequate 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?

The description explains the ticker mode (historical plus estimate), the from/to defaults and max, and the status meanings, adding value beyond the schema. It does not explicitly describe the limit parameter, but that is trivial; overall it compensates for the 40% schema 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 provides earnings calendar dates from US companies' 8-K filings, distinguishing ticker mode (historical since 2023 plus estimate) from calendar mode. It explicitly notes 'Dates only, no EPS or consensus,' which sharpens its purpose against siblings like economic_calendar and corporate_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?

It explains the two usage modes (with ticker vs without) and the meaning of date window and status parameters, giving clear context for when to call it. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

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

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

Since no annotations are provided, the description carries the full behavioral burden. It discloses that actual and previous prints appear only after release, that a unit field is present, that consensus figures are excluded, and that the default window is 'last 7 days to next 30.' This is substantial transparency, though response ordering and pagination are not addressed.

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

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

The description is a single dense sentence that front-loads scope, then lists release types, states output characteristics, and closes with the exclusion and default window. There is no filler or repetition of the title.

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 scope, source, output fields, exclusions, and default window, which is strong given the optional parameters and no annotations. Since there is no output schema, a bit more detail about timestamps, ordering, or how importance maps to release types would make it fully 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 schema documents from/to as YYYY-MM-DD and gives an enum for importance, while the description adds the useful default-window behavior that affects how missing from/to parameters are interpreted. This exceeds the bare schema, but importance is not semantically explained beyond its enum 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 specifies a precise resource: 'Scheduled US releases from the agencies' own calendars' and enumerates the covered categories (CPI, PPI, payrolls, FOMC, etc.). It also distinguishes itself by explicitly stating 'No consensus figures,' which separates it from calendar-like siblings.

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 the tool: for scheduled official US releases with actual/previous values, not consensus estimates. It does not explicitly name alternatives such as macro_series or earnings_calendar, so it stops short of a 5.

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

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

With no annotations, the description carries the behavioral burden and does disclose meaningful traits: data starts in January 2010, from/to/limit control the window, and there is an alternative mode returning the latest settlement's largest fails by value. It does not spell out output format or the exact trigger for the second mode, but the core behavior is 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 a single dense sentence that front-loads the resource and data fields, with the parameter behavior in a parenthetical and the second mode stated at the end. It is compact but slightly run-on; splitting into two sentences would improve readability.

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, so the description must convey return behavior, and it does list quantity and price by settlement date. However, it leaves ambiguity about when the second mode triggers and what the default behavior is when no symbol or date range is supplied, which is important given all parameters are optional.

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%, giving baseline 3. The description adds value by explaining that from, to, and limit jointly select the window and that the symbol parameter selects a FTD series, while the alternative mode connects to the optionality of parameters. This goes mildly beyond the schema's per-field 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 (SEC fails-to-deliver data), the fields (quantity and price), and the dimension (settlement date), and gives coverage since January 2010. It does not explicitly contrast this with sibling tools such as threshold_list or short_interest, so it stops short of full differentiation.

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 the tool is for retrieving SEC fails-to-deliver records and offers two modes: a date-window query for a symbol and a top-fails-by-value query for the latest settlement. It gives no explicit when-to-use versus alternatives or exclusions, so an agent must infer when this tool is appropriate.

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?

There are no annotations, so the description carries the burden of explaining behavior. It usefully discloses that results can be summed or filtered and that the data source is USAspending, implying a read-only query. However, it does not explain what 'largest' means in practice, what the default output is when no options are supplied, or whether the results are sorted or limited. This is adequate but has clear 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 entire description is one compact sentence that is front-loaded with the tool's core purpose and then provides the two key usage variations. There is no filler, repetition, or wasted 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?

For a tool with four optional parameters and no output schema, the description covers the primary purpose and two important parameters but omits days and listed semantics, default behavior, and any notion of result size or sorting. It is usable for common calls but not fully self-contained for an agent choosing parameters 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?

Schema description coverage is only 25%, so the description must compensate. It adds meaning to by=ticker and ticker: by=ticker sums by listed parent company, and ticker filters to one ticker. However, the days and listed parameters are not explained beyond their raw schema types, leaving some ambiguity about their exact 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 identifies the resource ('US federal contract actions from USAspending') and the core operation: retrieving the largest contract actions. It also distinguishes itself by focusing specifically on federal contract data, which none of the sibling tools reference. However, it lacks an explicit verb like 'get' or 'list', so it is clear but not maximally crisp.

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 concrete usage guidance for the main parameterization: using by=ticker sums by listed parent company, while ticker filters to one company. This tells an agent how to switch between aggregated and filtered modes. It does not explicitly rule out any alternative tools, but none of the visible siblings overlap directly with federal contract data, so no exclusion is necessary.

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 behavioral burden. It adds valuable behavioral facts: weekly frequency, oldest-first ordering, and the option to return either net liquidity or a single FRED series. It does not explain output shape, units, or what happens when series is omitted vs. 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 packs the formula, ordering, and series options into one sentence with no filler. It is dense but slightly overloaded; the long series list could arguably live in the schema, but it still earns its place given series is undocumented.

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 no output schema and no annotations, the description is reasonably complete on selection criteria and modes. It leaves ambiguous the return format, units, and whether 'components' are separate fields, which an agent would need when interpreting the result.

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 only 50%: series has no schema description, but the tool description compensates by listing the valid FRED series codes. The limit parameter is documented in the schema with default and semantics, and the description adds context for what the series parameter selects.

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 data: weekly US net liquidity with its formula, components, and ordering, or a specific FRED series. It doesn't use an explicit verb like 'retrieves,' and it doesn't explicitly distinguish this tool from siblings such as macro_series, though the formula and series list make the purpose 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?

No guidance is given on when to choose this tool over macro_series, funding_rates, policy_rates, or other data tools. The 'or one FRED series' clause describes two modes of the tool but not the selection context 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?

No annotations are present, so the description carries the full burden. It does add useful context: 'tracked' signals a curated manager list, and 'latest quarterly filing' discloses the data's point-in-time recency. However, it omits error behavior, what happens for unknown tickers, and the full response shape.

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 front-loaded sentence that packs purpose and output fields with zero waste. Every word 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?

Adequate for a simple single-parameter query tool that discloses its output fields. The main gap is the missing usage guidance versus siblings; without it the agent may struggle to route correctly between manager-level and holder-level tools.

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 ticker parameter already carries a clear description with examples (GME, BRK-B) and SEC class-share nuance. The tool description adds nothing beyond that, so the 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 uses a specific verb-resource pairing ('which tracked 13F managers held a ticker') and enumerates the returned fields (shares, value, share of portfolio, change). It names concrete managers (Berkshire, Bridgewater) which helps set it apart from large_holders and fund_portfolio, though it stops short of explicitly naming those siblings.

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 select this tool over the closely related siblings fund_portfolio or large_holders. The agent must infer that this is the manager-level view of a ticker, with no stated exclusions or alternative routing.

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. It discloses a non-obvious transformation (hourly venues shown as 8-hour equivalent) and the 'tracked crypto symbols' limitation. It does not mention rate limits, return structure, or behavior for invalid slugs, but the disclosed transformation is meaningful 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?

The entire description is one tightly packed sentence that front-loads the core purpose, then adds the exchange list, unit normalization note, and slug usage. Every phrase earns its place with no repetition 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?

For a single optional parameter with no output schema, the description covers the two invocation modes, the data source exchanges, the unit conversion, and slug examples. It does not enumerate tracked symbols or detail the output fields, but this is likely sufficient for correct tool selection and invocation.

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

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

The schema only defines slug as a string with maxLength 20 and no description. The tool description compensates by explaining that slug selects one symbol's history and provides concrete examples (btc, eth, sol). This gives the agent actionable meaning 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 states a specific resource and action: current perpetual funding rates across six named exchanges, or historical rates for a symbol by slug. It clearly identifies what the tool returns and is distinct from the other financial data siblings.

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 modes: omit slug for current rates, provide a slug for history. However, it does not explicitly state when to prefer this over sibling tools like crypto_market, nor does it mention 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, the description must disclose behavioral traits. It clarifies that it returns the latest portfolio and the fields included, implying a read-only operation. However, it does not mention any side effects, authentication requirements, rate limits, or data ordering/pagination. Since it's a simple retrieval, the lack of explicit read-only declaration is acceptable but could be more explicit.

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

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

The description is extremely concise, two sentences that front-load the core purpose and immediately provide concrete examples and expected output. No fluff or redundant information. Every word earns its place, making it easy for an agent to parse quickly.

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 parameter, no output schema, straightforward return), the description is sufficient. It tells the agent what to expect in the response (positions with value, shares, share of portfolio). It could mention ordering or error conditions, but these are minor for a lookup tool. The overall completeness is good but not exhaustive.

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 a description for the single slug parameter, achieving 100% coverage. The tool description repeats the example and adds context about tracked managers, but does not introduce new semantic details beyond the schema. With full schema coverage, the baseline of 3 is appropriate; the description offers marginal additional 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 states exactly what the tool does: retrieves the latest 13F portfolio for a specific tracked manager identified by slug. It provides concrete examples (berkshire-hathaway, bridgewater) and specifies the output content (positions with value, shares, and share of portfolio), making its purpose unmistakable. It also differentiates from siblings like fund_holders or large_holders by focusing on tracked managers.

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 well-known tracked managers but does not explicitly state when to use this tool versus alternatives such as fund_holders or large_holders. There is no mention of when not to use it or preferred scenarios. The examples hint at the intended audience but leave routing to the agent's inference.

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 behavioral burden and does substantial work: it restricts to Form 4 code P open-market buys, requires multiple distinct buyers, explains sort order, and states default thresholds for window and insider count. It still omits things like pagination and limit behavior, but the core filtering and output behavior are disclosed.

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

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

The description is compact and front-loaded: the first sentence defines the scope and outputs, and the second sentence adds defaults and ticker usage. It avoids boilerplate, though it does restate some default values already present in the schema.

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 gives enough context to invoke the tool correctly, including defaults, sorting, and returned fields, especially in the absence of an output schema. It is less complete on how this tool relates to sibling insider tools and on what the limit parameter controls, but these are not blocking 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 high at 80%, and the description adds value by stating defaults (30 days, 3+ insiders) and clarifying that ticker narrows to a single company. However, the limit parameter has no description in the schema and is not mentioned in the description, leaving one minor 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 clearly identifies the tool as finding companies where multiple insiders bought stock on the open market within a window, and lists the returned fields (buyers, titles, trades, combined value, dates). It does not explicitly contrast itself with sibling tools like insider_trades or planned_insider_sales, so it falls short of full differentiation.

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 no guidance on when to choose this tool over insider_trades, planned_insider_sales, or other insider-related siblings. The only usage hint, 'Use ticker to check one company,' addresses parameter usage rather than tool selection, and no exclusions or alternative conditions are stated.

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 of behavioral disclosure. It does reveal useful traits: data available since 2020, up to 2,000 rows, and the two modes. But it omits important behaviors such as what happens with no parameters, how 'latest' is defined, whether results are sorted, and what the response structure looks like.

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

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

The description is compact at two sentences, and the key output details are front-loaded. However, the second sentence is a long run-on that mixes the two modes into one clause; breaking it into separate sentences or bullets would improve scannability.

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

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

The tool has 6 parameters, 0 required, no output schema, and two distinct modes. The description fails to cover the window parameter entirely, does not explain parameter interactions (e.g., can ticker be combined with type?), and does not state defaults when no arguments are supplied. This leaves significant gaps for an agent deciding how to call 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 83%, so the baseline is 3. The description adds minimal beyond the schema: it groups from/to/limit as 'select the window' and explains type P/S, but the schema already conveys most of that. Critically, the window parameter is not mentioned in the description and has no schema description, so the meaning of '7d/30d/90d' remains unexplained.

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 insider transactions from SEC Form 4, lists the specific data fields (insider name/title, transaction code, shares, price, value, date), and distinguishes the two primary modes: ticker history and latest trades across companies. However, it does not explicitly contrast itself with sibling tools such as insider_clusters or planned_insider_sales, so it falls short of full differentiation.

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 conditions for using the two modes: from/to/limit for ticker history, and type P/S for latest trades across companies. It does not, however, provide any guidance about when to prefer this tool over sibling alternatives, nor does it state exclusions like 'do not use when tracking planned sales'.

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 present, so the description carries the burden of behavioral disclosure. It does state the data source (EDGAR), the included document types, and that listing status is returned. However, it does not describe response structure, pagination, update frequency, or whether the listing status is current or historical, leaving moderate transparency 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 dense sentence that front-loads the core document types and adds the source and listing-status enrichment with no wasted words. It is concise while still carrying meaningful 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?

The description is sufficient for an agent to identify the tool's domain and make a zero-parameter call, but it does not explain return values beyond 'listing status', lacks usage guidance, and leaves the 'days' parameter unexplained. Given the absence of an output schema and annotations, this is minimally viable but not 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 67%: 'new' and 'form' have descriptions, while 'days' only has type and bounds. The tool description adds no parameter-level meaning and does not compensate for the undocumented 'days' parameter. Since most parameters are already explained in the schema, 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 identifies the tool as providing EDGAR IPO-related documents: S-1, F-1, 424B4, EFFECT, and RW withdrawals, plus listing status. It lacks an explicit verb like 'retrieves' or 'lists', so it is not a full 5, but the resource and domain are unmistakable and distinct from the 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 specialized EDGAR IPO content implies when this tool should be used, but there is no explicit guidance about when not to use it or how it differs from related siblings such as corporate_events or private_placements. The intended use is evident, but the routing guidance is only implicit.

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 must carry the full behavioral disclosure burden. It adds meaningful context: the 5% threshold, the 13D vs 13G distinction (active vs passive), the cover-page source, and the returned fields. But it does not disclose behavior for omitted parameters, default sorting, date ranges, pagination, or output format, so an agent cannot fully anticipate call results.

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

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

The description is a single information-dense sentence that front-loads the critical facts: threshold, form types, and returned fields. The second clause is brief and clarifies usage. There is no filler or redundant restatement of the title, 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?

This tool has 4 optional parameters, no output schema, no annotations, and many sibling tools. The description defines the fetched fields and one usage pattern, but omits how days, form, and sort interact, what happens when no parameters are provided, and any default behavior or limitations. An agent would need to infer too much to invoke this correctly in all plausible scenarios.

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 25% (only symbol has a description). The description's clause 'For a symbol or the latest filings' loosely hints at symbol and possibly days, but it does not explain the semantics of days, form, or sort. With the schema leaving three parameters effectively undocumented and the description not compensating, an agent must infer too much to construct correct calls.

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 what the tool returns: 'Holders above 5% from Schedule 13D (active) and 13G (passive) cover pages' with fields 'holder, shares, percent of class, filing date.' It identifies a specific resource and distinguishes from generic fund-holder tools by regulatory form. It lacks an explicit verb like 'list' or 'retrieve' and does not differentiate from siblings by name, so it stops 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 phrase 'For a symbol or the latest filings' implies the two main invocation modes (by ticker or by recency), providing some usage context. However, it never explicitly states when to prefer this tool over alternatives such as fund_holders or insider_trades, nor does it mention exclusions, prerequisites, or when not to use it. Guidance is only implied.

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 behavioral disclosure. It does disclose that data is daily and filterable by series and date range, but it does not explain what happens with omitted parameters, default date behavior, output format, or invalid series names.

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 front-loads the core content and then states the filter capability. Every word contributes to understanding the tool; no filler 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?

The tool has no output schema and no annotations, and the schema only covers 33% of parameters. The description does not provide enough detail—such as valid series names, date range inclusivity, or behavior when parameters are omitted—for an agent to reliably construct a correct 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?

The input schema only documents 'from' with a date format, leaving 'to' and 'series' undocumented. The description adds meaning by grouping them as 'series name and date range,' which clarifies that 'to' is also a date and 'series' is the targeted series, but it still does not define accepted series values or exact date 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 identifies a concrete resource—US Treasury yield curve points, curve spreads, and stablecoin supply as daily series—and states that it can be filtered by series name and date range. This content clearly differentiates it from siblings like economic_calendar, policy_rates, and treasury_auctions.

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 when to use the tool through its content (daily macro series) but provides no explicit guidance about when not to use it or which sibling to choose as an alternative. The filtering mention is operational, not comparative.

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 the behavioral burden; it does clarify that these are pre-trade planned-sale notices and enumerates the data fields returned. However, it does not mention how the symbol/days parameters scope the results, data freshness, or that this is a read-only listing, leaving some behavior implicit.

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 that front-loads the filing type and packs the key attributes into a parenthetical; no filler or redundant restatement of the title. It is concise and scannable.

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 two-parameter tool this is close, but it lacks any explanation of the `days` filter and gives no routing cues against insider_trades/insider_clusters. With no output schema or annotations, the description alone does not fully cover the details an agent needs to pick and 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 coverage is 50%: `symbol` has an inline description, but `days` has only numeric bounds and no meaning, and the tool description never explains what `days` controls (e.g., lookback window). The description's field list adds no parameter-level guidance, so it does not compensate for the 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 names a specific SEC filing type (Form 144) and characterizes it as an affiliate's planned sale of restricted/control stock, listing the key fields (seller, shares, value, planned date). It also notes 'filed before the trade,' which distinguishes it from executed insider-trade tools such as insider_trades. No verb like 'list' appears, but the resource and scope are 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 conveys the domain (planned affiliate sales) but never states when to prefer this tool over siblings such as insider_trades or insider_clusters, and offers no explicit exclusions or alternate routing. The intended use is only implied by the filing-type definition.

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 behavioral burden. It does disclose that omitting 'country' returns the current table and providing a country code returns that country's history, with examples (us, eu, jp, gb). However, it does not mention output format, data frequency, or other behavioral traits like ordering or completeness.

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 entire description is one tight sentence, front-loading the core resource and scope, then using a colon to explain parameter-dependent behavior. No filler or redundancy; every word 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?

For a tool with one optional parameter, no output schema, and no annotations, the description gives the essentials but leaves ambiguity about the exact response shape (e.g., fields in the current table or history series). An agent could call the tool but may not know what data structure to expect, so it is only moderately 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 single parameter 'country' is fully explained: it is optional, takes short country codes like us/eu/jp/gb, and its presence switches between table and history modes. This goes far beyond the bare schema (maxLength 4) and gives the agent concrete usage guidance.

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 resource (policy rates) and scope (49 economies), and differentiates its two modes: current table vs. one country's history. It distinguishes itself from sibling tools like funding_rates or macro_series by topic, though it lacks an explicit verb like 'get' or 'list'.

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: if you need central bank policy rates, this is the tool. It gives clear context on how to request either the full table or a country's history, but it does not explicitly mention alternatives or when not to use this tool, leaving the agent to infer differentiation from 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?

With no annotations provided, the description carries the behavioral burden and does convey its main query orientations. However, it does not disclose defaults, how to explicitly activate the largest-raises mode, whether pooled funds are included by default, or what the response shape will be.

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 compact sentences with no filler: the resource and its fields come first, then the three usage modes are listed efficiently. Every clause adds useful 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?

For a four-parameter read tool with no output schema and no annotations, the description gives a useful overview but is not fully self-contained. An agent still has to infer how to invoke the largest-raises mode, the default time window or sort behavior, and whether funds are included without inspecting the 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 description coverage is only 25%, so the description partially compensates by implying that cik identifies an issuer, days defines a window, and sort=recent requests recent filings. It does not explicitly describe the funds parameter, but the schema already provides that description, so parameter meaning is only partially clarified.

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 (Form D private placement notices) and the key data it exposes: issuer, amounts, investors, and pooled fund status. It also lists the main query modes, which distinguishes it from the financial-data siblings, though it lacks an explicit verb such as 'get' or 'search'.

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 concrete usage contexts: largest raises in a window, one issuer by CIK, and most recent filings, which map naturally to the days, cik, and sort parameters. It does not explicitly name alternatives or say when not to use this tool, but no sibling tool is close enough to create real ambiguity.

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

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

With no annotations, the description carries the full disclosure burden and does well: it explains the data source cadence (FINRA settlement dates, twice a month), ordering (newest first), and the no-symbol fallback behavior. It does not detail edge cases or exact return field names, but for a read-only data lookup it 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?

Two dense sentences, no filler. The core metric set is front-loaded, followed by the important no-symbol behavior. Every phrase 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?

For a simple tool with two fully documented optional parameters and no output schema, the description is complete: it tells the agent what data fields are returned, the update frequency, the sort order, and the unparameterized fallback. An agent can invoke it correctly with the information provided.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds extra value by explaining what happens when symbol is omitted, which directly clarifies the optional symbol parameter, while limit's meaning and default are already fully documented in 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 names a specific resource (FINRA short interest for US stocks), lists concrete metrics (shares short, average daily volume, days to cover, change), and clarifies the no-symbol fallback. This clearly separates it from siblings like short_volume or fails_to_deliver.

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

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

Usage is implied rather than stated: the description makes clear this is for short-interest data, but it never explicitly says when to choose this over siblings such as short_volume or threshold_list. No exclusions or alternative tool mentions are provided.

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

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

With no annotations, the description must fully disclose behavioral traits. It mentions the data source and history window but omits important behaviors: it is read-only, but no explicit statement; it does not describe pagination, response format, error conditions, or data completeness. It also mentions 'limit' which does not exist in the schema, causing confusion. The absence of safety or side-effect disclosure is a gap.

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 and front-loads the core purpose, then describes modes. It is efficient with no filler. The only flaw is the avoidable 'limit' error, but from a conciseness standpoint, it is well-structured and readable.

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

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

Given no output schema, the description should clarify what the tool returns. It mentions 'short sale volume and total volume per symbol' and 'short share', but does not explain the response structure, whether pagination exists, or what the default behavior is when no parameters are supplied. The two modes are described, but without detail on sorting, limits, or error handling. The 'limit' error also reduces trust. For a tool with 4 parameters and no annotations, this is insufficient.

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?

While schema coverage is 100%, the description incorrectly references a 'limit' parameter while the schema has 'days'. It does add context like 'oldest first' and 'up to 5,000 days', but the erroneous mention of 'limit' undermines the accuracy. The description adds moderate value but includes a misleading term, so it does not improve on the schema adequately.

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 names a specific resource (FINRA Reg SHO files), a specific metric (short sale volume, total volume, short share), and the time range (since August 2021). It clearly differentiates from siblings like short_interest by focusing on daily volume from Reg SHO. The purpose is unambiguous.

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

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

The description explains two distinct usage modes: historical data for a symbol (with window selection via 'from', 'to', and 'days') and the latest day's largest short volumes. It gives clear context on how to invoke each, though it does not explicitly contrast with alternative tools (e.g., short_interest, fails_to_deliver). Still, the in-tool usage guidance is strong.

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 and does add useful behavior: daily files since 2022, the five-settlement-day definition, and the default date. However, it omits the return shape, how limit behaves, and whether the mention of only Nasdaq and Cboe conflicts with the nyse enum in the schema.

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 dense sentences with no filler: the first defines the tool, the second lists usage modes. It is concise and front-loaded, though the second sentence is telegraphic.

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 4-parameter tool with no output schema and no annotations, the description covers the core concept but leaves out important operational details: what the returned list contains, the role of limit, and whether the nyse market option is supported despite the Nasdaq/Cboe source phrasing. Adequate for basic calls, not 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 50%, so the baseline is 3. The description adds meaning for date (default newest), symbol (days on the list), and market (listing market), but says nothing about limit or how parameters may combine. It is helpful but does not fully compensate for the undocumented limit.

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 names the resource ('Reg SHO threshold lists'), defines the threshold condition, and states data sources with a temporal scope. It is specific enough to distinguish this from the raw fails-to-deliver tool, even though it never names a sibling.

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

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

The description explains the main query modes: one date (defaulting to the newest), one symbol, or one listing market, which gives the agent a concrete way to decide how to fill parameters. It does not explicitly mention alternatives or when-not-to-use cases, but the context is clear.

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

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

No annotations exist, so the description carries the full burden. It discloses the data source, a lookback boundary (since 2010), the default filtering behavior, and the semantics of upcoming=true. It omits things like update frequency or pagination behavior, but the core behavioral traits are well covered.

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, both information-dense and front-loaded with the core purpose and source. Every clause 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?

For a read-only retrieval tool with six optional parameters and no output schema, the description covers source, time range, default filter, upcoming behavior, and key returned fields. It does not explain how from/to interacts with upcoming or the default limit, but the schema handles parameter-level detail, making the description 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 schema covers 50% of parameters with descriptionsicki. The description adds meaning beyond the schema by explaining the default type (coupon auctions) and the behavior of upcoming=true, but it does not clarify limit, from/to interactions, or the 'all' enum value. It only partially compensates for the schema coverage gap.

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

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

The description clearly states the resource (Treasury auction results and calendar from TreasuryDirect) and the specific data fields returned, making the tool's purpose unambiguous. It does not explicitly distinguish itself from sibling tools, so it falls short of a top score.

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 offers in-tool usage context by explaining the default coupon auction filter and the effect of upcoming=true, which helps an agent use the parameters. However, it never mentions when to choose this tool over alternatives like economic_calendar or policy_rates, leaving tool selection to inference.

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