x402Pulse

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the data sources it fans out to, the three-level rating scale, and plain-language reason output. It still omits freshness/latency and whether results are cached, which matters for a live-data aggregator.

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?

Front-loaded with purpose, then composition, then output format, then scope. The source enumeration is long but each clause carries routing value. Slightly dense for a definition that could trade one clause for a note on the optional date.

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?

An output schema exists, so return values need not be described, and annotations cover safety. The description covers scope, sources, and rating output well. Remaining gaps are minor: what happens when the optional `date` is omitted and how stale the underlying live feeds may be.

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

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

Schema coverage is 100%, so baseline is 3. The description goes further by clarifying the destination's accepted form ('any airport worldwide by IATA code, e.g. SFO to LHR'), where the schema only says 'Destination airport' — though it slightly undersells `from`, which the schema allows as IATA or ICAO. It does not address whether `date` is optional.

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 a specific verb and resource with the exact output shape: 'rates the delay risk (low, moderate, high) for a flight between two airports on a date, with plain-language reasons.' An agent can immediately distinguish this composite risk-rater from siblings like get_airport_status, get_airport_forecast, and get_travel_advisory, whose data it consumes.

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?

'Combines live FAA delays and ground stops, ... weather and airport forecasts ... travel advisory, and the currency exchange rate' tells the agent this single call subsumes five sibling tools, which is strong routing context. 'Not for flight planning' adds an explicit exclusion, but no alternative tool is named for the flight-planning case.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered structurally. The description adds meaningful interpretive context beyond that: signals are disproportionality statistics, not causal evidence, and the output is not medical advice — context that prevents an agent from over-claiming 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 core method sentence is front-loaded and dense with useful specifics; the two trailing caveats are short and earn their place as interpretation guards. 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?

An output schema exists, so return-value explanation is unnecessary, and annotations cover safety and idempotency. For a one-parameter read tool, the definition is nearly complete; the only real hole is the absence of sibling differentiation against get_drug_safety.

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 single parameter ('Drug brand or generic name') is documented in the schema itself. The description adds no format, synonym, or normalization guidance 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 gives a specific verb+resource ('drug safety signal detection from FDA FAERS') and even names the statistical method (PRR, chi-square, Evans criteria), so the tool's function is unambiguous. However, it never distinguishes itself from the sibling get_drug_safety, which an agent could easily confuse with this detection tool.

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

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

It states the output is 'a statistical prompt for study, not evidence of harm' and 'not medical advice,' but that is interpretive framing, not usage guidance. There is no when-to-use versus alternatives, and crucially no routing to get_drug_safety, get_drug_label, or list_fda_recalls for adjacent questions.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, so the safety profile is covered. The description adds value beyond that by enumerating the returned data (lobbying amounts, trades, latest action, official link) and by flagging that links are correlational, not evidence of motive. It stops short of noting pagination or how limit interacts with result volume.

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 tight sentences with the payload described first and the search axes second; nearly every clause carries information. The leading phrase 'Bills in Congress linked to money' duplicates the title, a small redundancy, but overall it is well front-loaded and free of 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?

With an output schema present, the description needn't enumerate return fields, yet it does describe the payload shape; annotations cover the safety profile. What's missing for a fully complete picture is combination/filter semantics and result-set behavior (limit, pagination), which matters for an open-world search 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 100%, so all four parameters are documented in the schema itself; the description merely restates the search axes (ticker, member, bill title/number). It adds no new semantics such as whether multiple filters are ANDed or how the string-typed limit behaves, so baseline 3 applies.

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

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

The description names a specific resource and a specific join: bills in Congress plus the companies that lobbied on each bill (with amounts) plus trades by members in those companies' stocks, plus latest action and official link. This is clearly distinguishable from siblings like list_congress_trades (trades only) or list_corporate_lobbying (lobbying only), so an agent knows this is the cross-linked view.

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 concrete entry points ('Search by ticker, member or bill title/number') and an epistemic caveat ('For research, not proof of motive'), which implies usage. But it never says when to prefer this over list_congress_trades, list_congress_holdings, or list_corporate_lobbying, nor does it state 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?

Annotations already cover safety (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real behavior: a 30-market scan scope, a 15-minute refresh cadence, an evidence-thinness adjustment, and a low/medium/high confidence output rating. These freshness, scope and data-quality traits are not derivable from the annotations.

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

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

Purpose is front-loaded and each clause (scan scope, cadence, evidence tempering, confidence rating) carries distinct meaning. It is dense as a single long sentence but has no filler; the disclaimer earns a short trailing slot.

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

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

With an output schema present and annotations covering the safety profile, the description only needs to convey scope, cadence and the nature of the returned signal, all of which it does. Nothing an agent needs to call it correctly is missing.

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

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

Schema coverage is 100% with both optional parameters (limit, category) fully described and one enum constrained, so the schema carries the semantics. The description adds no syntax or format detail beyond what the schema provides, making the baseline 3 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?

States a specific verb (scans/returns) and resource (Polymarket markets where smart money disagrees with the price-implied probability), with a precise signal definition. This is clearly distinguishable from siblings like get_smart_money or get_whale_trades, which surface trader activity rather than price/smart-money divergence.

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 a screening use case (finding mispriced markets) and gives a clear trigger condition (money implies a different probability than price), but never states when to prefer this over alternatives such as get_smart_money or list_attention_markets. Usage must be inferred rather than being explicitly routed.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuine behavioral context beyond them: the forecast horizon, the period-by-period breakdown, the delay-risk rating, and the specific hazard flags (low clouds, storms, snow, strong gusts) that trigger alerts.

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?

Front-loaded with the resource and the horizon, followed by the field list and then the exclusion. A single dense but purposeful sentence plus a short scoping caveat; the detail is justified by the breadth of the output.

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?

An output schema exists, so return formatting is not the description's burden, and the description still previews the fields and hazard flags. What is missing is routing to adjacent siblings and any note on units or code format, but for a one-parameter read tool this is close to 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?

Only one parameter and schema description coverage is 100%, so the schema already documents the accepted IATA/ICAO airport code. The description's only addition is the 'any airport worldwide' scope statement, which is marginal beyond the schema; 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?

Names a specific verb+resource (airport weather forecast), scopes it precisely ('next 24 to 30 hours at any airport worldwide'), enumerates the returned fields (wind, gusts, visibility, cloud ceiling, flight category, delay-risk rating) and the flagged hazards. It is clearly distinguishable from siblings like get_airport_status and get_weather_forecast without opening either schema.

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

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

Provides an explicit exclusion ('Not for flight planning') which is real routing guidance, so the agent knows one class of intent this does not serve. However, it names no alternative sibling (get_weather_forecast, get_airport_status, check_trip_delay_risk) for the adjacent use cases it implies.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: data-source coverage limits per region and the fact that private-aircraft-only restrictions are specially labeled. No auth, rate-limit, or freshness details are given, but none are critical for a read-only snapshot.

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 content is front-loaded with the core purpose, then coverage caveats, then the exclusion. It is dense but each clause carries information; the parenthetical about private-aircraft labeling is slightly tucked away but 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?

With an output schema present, the description need not explain return values, and the annotations cover the safety profile. Combined with the coverage boundaries and the 'not for flight planning' exclusion, an agent has enough to call this correctly; only explicit routing to forecast/planning alternatives 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 description coverage is 100% and the single parameter already documents 'Airport code (IATA or ICAO)'. The description adds nothing about the parameter's format or edge cases, so this sits at the baseline for a fully documented 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 (airport status) and enumerates the exact contents: FAA delays, ground stops, ground delay programs, closures, weather, and a delay-risk rating. It implicitly separates itself from siblings like get_airport_forecast by emphasizing 'right now'/'current', but it never names an alternative tool, so the sibling differentiation is inferred rather than stated.

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 clear exclusions ('Not for flight planning') and coverage boundaries ('FAA data covers U.S. airports; weather covers airports worldwide'), which tell the agent when this tool does and does not apply. It stops short of pointing at the correct alternative for forecasting or planning, which would be required for a 5.

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

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

Annotations already establish that this is a read-only, idempotent, open-world, non-destructive operation. The description adds useful behavioral context about the two output modes and a brief disclaimer, though it does not discuss auth, rate limits, or pagination.

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: core retrieval behavior comes first, followed by the two modes and a short disclaimer. There is little 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?

Given three optional parameters, full schema coverage, rich annotations, and an output schema, the description is complete enough for correct invocation. It covers both modes and the nature of the data without needing to restate schema details.

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 schema already defines limit, ticker, and minRatings. The description adds meaning for the ticker parameter by explaining the mode switch, but it does not add semantics for limit or minRatings 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?

Clearly states that this returns app-store ratings for public companies' apps and distinguishes the ticker mode from the no-ticker mode. The resource and scope are specific enough to separate it from sibling financial-data 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?

Explains when to provide a ticker versus when to omit it, including what each mode returns. It does not name a sibling alternative or explicitly state when not to use it, 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the data windows (latest quarter, trailing year, 90 days), the trade-type distinction (open-market vs. pre-planned 10b5-1) and cluster-buy detection. It does not disclose filing freshness or call latency, keeping it short of a 5.

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?

Purpose is front-loaded in the first clause, followed by a tightly packed content list and two short closing sentences. Every clause carries information, though the middle enumeration is dense enough to read as a wall of text.

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

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

With an output schema present, the description needn't explain return values, and the annotation set covers the safety profile. What remains — the exact contents of the brief, the ticker scope, and the data windows — is fully specified, so an agent has everything needed to call 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?

There is a single parameter with 100% schema description coverage, so the schema already documents it. 'Any U.S.-listed ticker' largely restates the schema's 'U.S. stock ticker' and adds only a marginal scope confirmation, so baseline 3 applies.

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

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

The description states a specific verb and resource and then enumerates exactly what the brief contains: quarterly and trailing-year financials, 90-day insider activity, 8-K events, 5%+/activist stakes, and a plain-language summary. The phrase 'in one call' explicitly distinguishes it from the granular siblings (get_company_financials, list_insider_trades, list_company_events), so an agent can route without opening any schema.

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?

Scope is given ('Any U.S.-listed ticker') and a disclaimer is included, but there is no explicit when-to-use/when-not guidance and no named alternative. The aggregation intent only implies that an agent should prefer this over calling the granular sibling tools separately.

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

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

Annotations already declare the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true). The description adds a useful behavioral trait: it handles companies that changed reporting labels. It also includes a disclaimer ('Data, not investment advice'), but omits other behavioral details such as authentication requirements or rate limits. With annotations covering the core safety information, this is a moderate addition.

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

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

The description is front-loaded with the key data scope and is structured as three sentences with no wasted words. The first sentence is long but efficiently lists the returned metrics; the second and third add relevant context concisely.

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

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

Given that an output schema exists (so return values need not be described) and annotations cover the safety profile, the description is complete enough for correct invocation. It thoroughly specifies the data universe, time ranges, and metrics, and notes handling of label changes.

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

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

Schema description coverage is 100% for the single ticker parameter, so the schema already provides clear semantics. The description adds no further parameter-level meaning, making the baseline of 3 appropriate.

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

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

The description clearly states the resource (standardized company financials from SEC XBRL filings) and enumerates the specific metrics and time periods returned. However, it does not explicitly differentiate this tool from sibling get_company_brief, which likely serves a similar but broader purpose.

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 when-to-use guidance is provided. The description does not mention when to choose this tool over alternatives like get_company_brief, nor does it state any 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful content scope and a 'not investment advice' caveat, but it does not discuss pagination, auth, rate limits, or other behavioral traits beyond what the structured metadata and output schema already provide.

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

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

The description is front-loaded with the core resource and then compactly enumerates the returned signal dimensions. Every sentence adds context, and the final disclaimer is brief and purposeful.

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 rich annotations, 100% schema description coverage, and an output schema, the description is complete enough for an agent to select and invoke the tool. It also usefully summarizes the data shape without needing to duplicate the output 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 100%, so ticker, days, and limit are already documented in the schema. The description does not add parameter-specific meaning beyond implying company/ticker filtering, which is the expected baseline when the schema carries parameter 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 states a specific resource and scope: U.S. patents granted to a company, with counts, quarters, trends, patent types, and latest patents. It is clearly distinguishable from financial, event, and trading siblings because no other sibling covers patents.

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 'An innovation-pace signal' gives clear usage context for when an agent should reach for this tool. It does not name exclusions or alternatives, but the surrounding sibling set contains no direct patent alternative to route against.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds a useful disclaimer ('Facts, not investment advice') but omits material behavior: how stale disclosure data is, whether a name search can return multiple members, and what days/limit default to.

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?

One compact sentence block that front-loads the resource and its contents; the trailing disclaimer is short and intentional. No filler.

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

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

With an output schema present, the description does not need to specify return shape and correctly focuses on scope plus identification. The remaining gap is lookup ambiguity and data freshness, which matter for a disclosures tool but are minor against the annotations.

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

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

Schema coverage is 100%, so all four parameters are already documented. The description only restates the name-or-id choice, adding no semantics for days, limit, or precedence when both id and member are supplied.

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 a concrete resource (a single member of Congress) and enumerates the payload: party, chamber, state, net worth, trades, holdings. This distinguishes it from list-style siblings such as list_congress_trades, though it never names those siblings explicitly.

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?

'Find them by name or id' gives lookup guidance but says nothing about when to choose this profile tool over list_congress_trades, list_congress_holdings, or get_whale_trades, nor what to do on ambiguous name matches.

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

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive, open-world), so the description does not need to restate those. It adds useful behavioral context beyond annotations by clarifying that prices are end-of-day rather than live and that closes are split- and dividend-adjusted, plus a 'not investment advice' disclaimer.

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

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

The description is front-loaded with the core resource and return contents, followed by two short scoping sentences. It is dense but appropriately sized for a data-retrieval tool with many returned fields; the closing disclaimer earns its place by preventing misuse as investment advice.

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?

An output schema exists, so the description need not explain return formatting, and annotations already carry the safety profile. For a two-parameter read-only price tool, the description supplies the key context an agent needs: EOD timing, adjustment treatment, non-live nature, and a usage disclaimer.

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 schema already documents both parameters, including the ticker example and the 1-to-730 days range. The description adds only that daily bars cover 'the period you choose,' which is marginal beyond the schema and does not provide additional format or constraint detail.

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 the specific resource (end-of-day stock prices) and enumerates the exact data returned: OHLCV, multi-period percentage changes, 52-week range, average volume, and daily bars. It also distinguishes itself from live quote tools by stating 'Not live quotes,' so an agent can identify it without opening the schema.

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 historical/daily equity price data and explicitly excludes live quotes, which helps scope usage. However, it does not name alternatives such as company financials or other price tools, nor does it give explicit when-to-use guidance beyond the 'Not live quotes' exclusion.

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

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds meaningful context beyond that: the data source (openFDA), the output shape ('clean structured text'), and a 'Not medical advice' disclaimer. It does not mention coverage limits, freshness, or error/not-found behavior, so not a 5.

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 the resource, the returned fields, the source, and the disclaimer with essentially no filler. It is dense but every clause carries information; the only minor cost is that one long list-heavy sentence is slightly harder to scan than segmented phrasing.

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

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

Output schema exists, so return values need not be explained, and the annotations carry the safety profile; combined with a single fully documented required parameter, an agent has what it needs to call this correctly. The description also covers source and the medical-advice caveat. Only minor disambiguation against the drug-safety siblings 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 description coverage is 100% and the single parameter is already documented as 'Drug brand or generic name'. The description's mention of 'brand and generic names' and 'any drug' restates rather than extends that, so the baseline 3 for full schema coverage 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?

States a specific verb+resource ('FDA drug label lookup') and enumerates the exact content returned: boxed warning, indications, contraindications, warnings, interactions, brand/generic names, manufacturer, route. This distinguishes it implicitly from drug-safety siblings like get_drug_safety and detect_drug_safety_signals, since it retrieves the regulatory label rather than signal/metric data. It never names those siblings explicitly, so it falls short of a 5.

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

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

'for any drug' establishes scope but no when-to-use guidance, no exclusions, and no reference to the closely related get_drug_safety / detect_drug_safety_signals / list_drug_approvals siblings an agent must choose between. Usage is left to inference from the field list.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds real interpretive context beyond them: the data source (FDA FAERS), the caveat that reports are not proof of causation, and that it is not medical advice — meaningful for correctly framing the numbers to a user.

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?

Front-loaded with the resource and its contents in one dense sentence, followed by two short disclaimer clauses that each earn their place by preventing causal misreading. Slightly list-heavy but no wasted 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?

With an output schema present and full parameter coverage, the description need not explain return values, and it still names the fields and source. The only missing piece is guidance on how it relates to the sibling drug 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?

There is a single required parameter at 100% schema description coverage, so the schema already carries the specification. The description's '(brand or generic name)' simply restates the schema's own parameter description, adding no new syntax or format detail. 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 gives a specific verb+resource ('FDA drug safety snapshot') and enumerates the concrete payload (total adverse event reports, serious/fatal share, top side effects, quarterly trend from FAERS). It does not, however, distinguish itself from the sibling detect_drug_safety_signals or list_drug_approvals, so an agent must infer 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?

Usage is only implied by 'for any drug (brand or generic name)' — the agent is told what input it accepts but not when to prefer this over detect_drug_safety_signals or get_drug_label. No exclusions or alternative routing 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?

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's job is to add data characteristics — and it does: the source (ECB), the update cadence implied by 'daily', the breadth (~30 currencies), and the crucial caveat that these are reference rather than tradable rates. It does not discuss latency, caching, or weekend/holiday availability, which keeps it short of a 5.

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 compact sentences, front-loaded with the resource and source, followed by usage context and a limitation caveat. No filler, no restatement of the title, and every clause carries 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?

An output schema exists, so return-value documentation is unnecessary, and both parameters are fully described in the schema. The description supplies the missing context — provenance, coverage, default behavior, and the reference-vs-trading distinction — so nothing an agent needs to call this correctly is absent.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: it establishes that the base currency is configurable to 'any base' with a USD default, which the schema only expresses as '3-letter currency code' with no default stated. That is genuine added value for an optional 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?

States a specific verb+resource (retrieves official exchange rates), names the authoritative source (European Central Bank daily reference rates), quantifies the scope (~30 currencies), and distinguishes itself from trading-rate tools in the same breath. An agent can select it confidently without opening the schema.

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 'Reference rates, not trading rates' gives an explicit when-not condition, and 'converted to any base currency (USD by default)' clarifies the expected invocation shape. There are no direct FX siblings to route against, so the absence of named alternatives is not a real gap.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered without the description. The description adds the data provenance ('proxy statement') and the 'latest year' scoping plus a not-investment-advice disclaimer, but says nothing about coverage limits, lag, or what happens when a company has no proxy filing.

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?

It is a single front-loaded sentence with no filler, but a large share of it enumerates return fields that the output schema already defines, so much of the text does not earn its place. The trailing disclaimer is short and defensible.

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

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

With an output schema present, the description need not explain return values — yet that is most of what it does. For a simple two-parameter read tool the coverage is adequate, but the absence of any selection guidance against the many sibling company/financial tools leaves a real gap.

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 both parameters (ticker, years) are already documented, and the baseline is 3. The description's mention of 'the latest year' and 'the CEO's pay history' gives indirect context for the years parameter but never explains its range or default, adding little 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 names a specific resource — executive compensation as reported in the company's proxy statement — and enumerates the components (named-executive salary/bonus/stock/options/total, CEO pay plus YoY change and stock share, CEO history). That is distinguishable from general siblings like get_company_financials. It lacks an explicit verb (e.g. 'Returns'), so it reads as a content list rather than an action 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?

There is no guidance on when to use this tool versus alternatives, no mention of get_company_brief or get_company_financials as complements, and no stated prerequisites such as which companies file proxy statements or how far back data goes. The only usage-adjacent line is the liability disclaimer 'Data, not investment advice.'

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds useful context beyond that: it identifies the authoritative government source and adds a 'Not medical advice' disclaimer, though it says nothing about rate limits, freshness, or what happens on a failed lookup.

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?

Front-loaded with the resource and scope in the first clause, then progressively narrows to content, lookup keys, and a disclaimer. The long middle enumeration of measures is dense but each item is informative; the only mild waste is restating return fields that the output schema already carries.

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

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

With an output schema present, the description need not explain return values and correctly focuses on identity, source authority, scope, and lookup keys. An agent has enough to select and call this tool correctly against a large sibling list.

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 reinforces the key semantics of combining 'name plus state' versus using a CMS facility ID, which adds slight value, but it introduces no format or validation detail beyond the schema's own parameter 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?

States a specific verb+resource ('Hospital scorecard for any U.S. Medicare hospital'), names the data source (CMS), and enumerates the scope of content (star rating, ownership, mortality/safety/readmission comparison, state rank/percentile). This clearly distinguishes it from the sibling rank_hospitals, which produces rankings rather than a single facility's scorecard.

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?

Gives a concrete lookup instruction ('Look up by CMS facility ID or name plus state'), which tells the agent how to invoke it, and implicitly covers the two alternative key paths. It stops short of naming when to prefer this over rank_hospitals or stating exclusions, so it falls below the explicit when/when-not bar 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety and determinism profile is covered. The description adds genuinely useful behavior beyond that: refresh cadence (three times a day), the fixed scope of the universe (28 named companies), and the sourcing of signals. It stops short of describing freshness/staleness windows or failure behavior, which is why it is not a 5.

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 core subject and universe are front-loaded in the first clause, followed by contents and cadence, so the reader can stop early. It is a single dense sentence with a long parenthetical, and the named example companies ('from SanDisk and Micron to CrowdStrike and Lam Research') are the one element that costs more space than it earns. Otherwise little 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?

An output schema exists, so return-value detail is unnecessary, and the description supplies the context an agent actually needs: what the brief contains, how fresh it is, and that the coverage universe is a fixed 28-company list. The main residual gap is the lack of any pointer to sibling tools for drilling into a single company or signal.

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 nothing for the schema or description to disambiguate. Baseline for a 0-parameter tool is 4, and the description correctly refrains from inventing parameter-like inputs (no ticker, no date filter), which itself communicates that the call is fully static.

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 (a daily brief on a fixed 28-company universe) and enumerates its contents: SEC-filing signals, per-company one-liners, and a macro backdrop. That is far more than a tautology and makes the composite nature clear. It does not, however, explicitly contrast itself with overlapping siblings such as get_company_brief, list_insider_trades, get_yield_curve, or get_smart_money, so an agent must infer 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?

Usage is implied rather than stated: 'Refreshed three times a day' signals a recurring daily overview, and 'Data, not investment advice' sets expectations. But there is no explicit when-to-use, no when-not-to-use, and no named alternative for agents that want a single company or a single signal type. Implied usage only.

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

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. The description adds substantive content context beyond that: the comparison against the stock's own 20-day average and the 'latest trading day' scope for the market-wide mode. It does not mention rate limits or pagination, keeping it just short of a 5.

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 covers both modes economically, with the 'Data, not investment advice' disclaimer earning its place as a constraint. It is slightly dense but contains 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?

An output schema exists, so return-value structure need not be explained, and annotations cover the safety profile. The description fills the remaining gaps by specifying what metrics are computed in each mode and the 20-day baseline comparison. Only minor operational details (e.g., default window behavior) are left implicit.

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 schema already documents days, limit, ticker, and minVolume (including that minVolume is market-wide only). The description's ticker-conditional behavior largely restates what the schema says ('optional; without it: market-wide leaders'), adding little semantic value beyond the schema baseline.

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

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

The description states the specific resource (off-exchange/dark pool trading), the exact metrics returned (daily off-exchange volume and short volume, short share vs its own 20-day average), and the two operating modes (single ticker vs market-wide leaders). An agent can tell exactly what data this returns without opening the schema.

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 clearly delineates the two usage modes: provide a ticker for per-stock daily series, or omit it to get the latest day's highest off-exchange short share and volume leaders. It does not name any alternative sibling tool or state when not to use it, but the mode split gives strong practical guidance.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely new behavioral context beyond those hints: the upstream source (EIA Weekly Petroleum Status Report), the weekly cadence, and the exact comparative metrics returned (build/draw, YoY, 5-year average).

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?

Front-loaded with resource and source before the long enumeration, which is the right ordering. The single dense sentence plus a short disclaimer earns its length, though the ingredient list is long and could be trimmed without losing routing value.

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

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

For a zero-parameter retrieval tool with a rich output schema and full annotation coverage, the description supplies enough: source, cadence, scope and contents. Return-shape details are legitimately left to the output schema, so only the absent sibling differentiation keeps this from a 5.

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 per the rubric the baseline is 4. The description adds no pseudo-parameters or hidden options, and simply describes the payload, which is appropriate for a no-argument snapshot tool.

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

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

Names a specific resource (U.S. oil inventories) and source (EIA Weekly Petroleum Status Report), and enumerates the exact contents: commercial crude, Cushing, SPR, gasoline, distillate, plus build/draw and comparative deltas. This is clear enough that an agent knows it's a stocks/inventories feed, but it never explicitly positions itself against the nearby oil siblings (get_oil_supply, get_oil_prices, get_oil_positioning).

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 when-to-use guidance and no alternatives named. 'Data, not trading advice' is a disclaimer about how to interpret the output, not a routing rule, so an agent gets no signal about when this beats get_oil_supply or get_oil_prices.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the agent knows the safety and side-effect profile. The description adds nothing behavioral beyond that (no data freshness, update cadence, or source caveats); the trailing 'Data, not trading advice' is a disclaimer rather than operational 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?

A single front-loaded sentence delivers the source (CFTC COT) and the full metric set with no filler, and the disclaimer is short. It is dense to the point of being a run-on list, which slightly hurts 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?

For a no-argument, read-only tool with an output schema and full annotation coverage, the description is essentially complete: source, instrument, metric list and the analytical framing (percentile vs 3 years) are all present. Only the lack of sibling routing keeps it short of a 5.

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 per-parameter semantics to explain; the baseline for a parameterless tool is 4. The description correctly does not invent arguments and instead spends its words on the returned content.

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 verb-resource pair ('WTI crude oil positioning from the CFTC Commitments of Traders') and enumerates the exact metrics captured (managed money long/short/net, weekly change, ratio, 3-year percentile, producers, swap dealers, open interest). This clearly separates it from get_oil_prices and get_oil_inventories by subject, but it never names or explicitly contrasts a sibling tool.

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

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

Usage is only implied — an agent can infer this is for positioning/sentiment analysis rather than price or supply questions, but the description gives no explicit when-to-use statement, no alternatives, and no conditions under which another oil tool is preferable.

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

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds worthwhile behavioral context beyond that: the source (EIA), that figures are official daily/end-of-day rather than live futures, and that this is data not advice. It stops short of noting update cadence or rate limits.

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?

Front-loaded with the resource name, then a single dense clause enumerating contents, then two short qualifiers. Every sentence earns its place, though the contents list is packed and could be trimmed slightly.

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

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

For a parameterless read tool with a full output schema and covering annotations, this is nearly complete: it identifies the source and enumerates the metrics returned. The only real gap is sibling differentiation, which is out of scope for this dimension.

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, which is the baseline-4 case. There are no inputs whose semantics need explaining, and the description correctly spends its words on output content instead.

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 a specific resource (crude oil prices) with concrete scope: WTI and Brent daily spot prices from EIA, plus changes, 52-week range and the Brent-WTI spread. This clearly distinguishes it from price-unrelated oil siblings like get_oil_inventories or get_oil_supply, but it never explicitly names or contrasts those 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?

There is no explicit when-to-use guidance and no routing to alternatives such as get_oil_supply or get_oil_positioning. The 'not live futures quotes' and 'not trading advice' lines are caveats about the data's nature, not selection guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so safety is covered. The description adds genuine context beyond that: the EIA weekly source and cadence, the units of measure (thousand barrels per day), and an explicit 'Data, not trading advice' scope disclaimer. It does not state freshness/lag or pagination, so not a 5.

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 leads with the source and resource before enumerating metrics. It is dense but every clause earns its place; the trailing disclaimer is short and functional.

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

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

With an output schema present, the description need not explain return values, yet it usefully previews the metric set anyway. For a zero-parameter read-only tool this is close to complete; only the relationship to sibling oil tools is unaddressed.

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 the baseline of 4 applies; there is nothing for the description to disambiguate. The listing of returned metrics is extra context rather than parameter 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 names a specific verb (get) and resource (U.S. oil supply) and enumerates the exact metrics returned, so the agent knows what this tool produces. It does not, however, contrast itself against the closely-related siblings get_oil_inventories or get_oil_positioning, leaving the boundary between 'supply' and 'inventories' to inference.

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 statement of when to reach for this tool versus get_oil_inventories, get_oil_prices, or get_oil_positioning, and no prerequisites or exclusions are given. The only guidance is the implicit scope in the data list, which is not enough to route among four oil-related siblings.

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

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

Annotations already cover the safety profile (readOnly, idempotent, destructive=false), so the bar is lower. The description does add useful domain semantics — the 'Solid or Sharp' skill taxonomy and the per-trade fields returned (skill score, edge, return, specialty) — but says nothing about the recency window for 'recent', default limit, or whether results are paginated.

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?

One substantive sentence that front-loads the resource and scope, followed by a short positioning line that earns its place. No filler, though the second sentence is closer to marketing than specification.

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?

An output schema exists, so return fields need not be enumerated, and annotations cover safety. The description supplies the key filter semantics; the only real gap is the undefined time window behind 'recent' and the unstated default for 'limit'.

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

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

Schema coverage is 100%, so both 'min' and 'limit' are already documented in the schema. The description adds no syntax, unit, or default information beyond it, which makes the baseline 3 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?

States a specific verb+resource with a scope qualifier: 'recent large trades by skilled (Solid or Sharp) traders only'. This is clearly narrower than the sibling get_whale_trades, though it never names that sibling or any other, so differentiation must be inferred from the 'skilled only' filter.

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

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

Implies the use case ('Separates informed whales from big gamblers'), which suggests an analyst chasing high-signal flow rather than raw activity. But there is no explicit when-to-use, no exclusion against get_whale_trades, get_smart_money or list_top_traders, and no stated prerequisites.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, so the safety profile is fully covered by structured data. The description adds some behavioral value by describing the analysis it performs (skill scoring, lean, agreement with odds) and the disclaimer, but says nothing about data freshness, latency, or limits. With annotations carrying the safety load, a 3 is appropriate.

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

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

Two front-loaded sentences that enumerate output content, followed by an accepted-input note and a brief disclaimer. It is efficient overall, though the parenthetical skill list ('edge, win rate, ROI') is slightly listy and duplicated by the output 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?

For a single-parameter, read-only, idempotent tool with a full output schema, the description covers what the tool returns and what it accepts. It need not explain the return shape since an output schema exists, and nothing essential for correct invocation is missing; only cross-sibling disambiguation is absent.

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

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

Schema description coverage is 100% for the single 'market' parameter, and the description's 'Accepts a market link, slug or condition ID' merely restates the schema's own description. No format examples, validation rules, or failure behavior are added beyond the structured field. Baseline 3 applies when the schema does the heavy lifting.

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 clear resource (Polymarket smart money for one market) and enumerates the specific output (biggest holders per side, scored for edge/win rate/ROI). It is specific and concrete, but it does not differentiate itself from closely named siblings such as get_skilled_whale_trades, get_whale_trades, or get_wallet_scorecard, which an agent could easily confuse it with.

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 when-to-use or when-not-to-use guidance and no named alternative. The closest thing to usage context is 'for one market', which implies scoping but does not tell the agent how to choose this tool over the whale-trade siblings. The final disclaimer ('Data, not investment advice') is not usage guidance.

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

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new behavioral context: the underlying data source (Wikimedia pageview data, CC0) and the range/latency constraint of 7 to 90 days. It doesn't mention caching, rate limits or data latency, which keeps it from a 5.

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?

One dense, front-loaded sentence that leads with what the tool returns before the input guidance. Efficient with no filler, though the long parenthetical enumerating entity types and outputs makes it slightly heavy to parse.

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

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

With an output schema covering return values and annotations covering the safety profile, the description only needs to add the entity scope, the title-exactness caveat and the data provenance - all present. An agent has everything required to call 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 100%, so title/lang/days are already documented in the schema, making 3 the baseline. The description only reinforces the exact-title requirement and the 7-90 range with an example ("Bitcoin") but adds no format or fallback semantics 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?

States a specific verb+resource: daily Wikipedia pageviews for one article, scoped to a titled entity and 7-90 days, returning baseline, latest-vs-baseline, spike days and 7-day trend. This distinguishes it clearly from aggregate siblings like list_trending_topics, list_attention_spikes and list_attention_markets.

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?

Gives a concrete usage instruction ("Use the exact article title, e.g. Bitcoin") which is the main failure mode for this tool. It doesn't name alternatives or when-not conditions (e.g., use list_attention_spikes for pro-active discovery), 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?

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety behavior is covered by structured data. The description adds useful content-level semantics (the meaning of levels 1-4), but says nothing about freshness, caching, or sourcing cadence that an agent might need beyond the safety profile.

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, front-loaded with the resource and immediately followed by return content, query modes, and formats. 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?

With an output schema present, annotations covering safety, and 100% parameter coverage, the description only needs to orient the agent — which it does, covering both the single-country and threshold-list modes. Minor gap: it does not warn about level drift/update timing for an openWorld advisory source.

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

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

Schema coverage is 100%, so both parameters are already documented in the schema. The description reinforces this with concrete format examples (MX, GB, JP) and the level scale, but adds only marginal meaning beyond what the schema states. Baseline 3 applies when the schema does the heavy lifting.

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?

Names a specific resource (U.S. State Department travel advisories) and states exactly what is returned: a country's level (with the full 1-4 scale named), summary, and main risk factors, or a filtered list of countries. This is distinguishable at a glance from siblings such as get_airport_status or check_trip_delay_risk.

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 the two operating modes explicit — look up a single country, or list every country at or above a given level — which tells the agent when each parameter applies. It stops short of naming alternatives or exclusions, so it is clear context rather than full when/when-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?

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds a genuinely non-obvious behavioral fact: the score is computed over only the latest 200 finished bets and includes losses, so an agent knows the score is a bounded sample rather than lifetime performance.

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

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

Two sentences, front-loaded with the resource and its metric payload, followed by the sampling caveat. The colon list is dense but each metric earns its place; nothing is padding.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile; the description supplies the one thing structured fields can't — the 200-bet/losses-included methodology. It is essentially complete for a single-arg read tool, with sibling routing left out.

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?

One parameter with 100% schema coverage (pattern plus 'Polymarket proxy wallet address' description), so the schema carries the load. The description's 'for any wallet' adds no format or constraint detail beyond it — baseline 3 is appropriate.

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

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

States a specific verb+resource ('scorecard for any wallet') and enumerates exactly what the scorecard contains — skill score, edge, win rate vs implied, ROI, realized PnL, specialty, largest open positions. That makes it easy to tell apart from list_top_traders and get_skilled_whale_trades, though it never names a sibling to route against.

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 statement of when to use this over list_top_traders, get_skilled_whale_trades, or get_whale_trades, and no prerequisites or exclusions. The only scoping note ('latest 200 finished bets') describes method, not 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?

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: data sources (MET Norway worldwide, NWS for U.S.), the extra narrative forecast and active alerts for U.S. locations, and the unit conventions. It does not discuss rate limits or failure modes, but the added sourcing detail is substantive.

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, front-loaded with the capability and then the source/regional caveats; little waste. The parenthetical field list is compact rather than padding, though the single long second sentence is somewhat overloaded.

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?

An output schema exists, so return-value documentation is unnecessary. For a zero-required-parameter, read-only lookup the description covers output scope, units, sources, and regional behavior well. The main gap is routing versus overlapping siblings like get_airport_forecast.

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 only marginal semantic value — it clarifies that coordinates or an airport code are the locators and that output is in °C and °F — but says nothing about the roles of tz, name, or precedence between airport and lat/lon.

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 a specific verb+resource with rich scope: current conditions, 12-hour and up-to-9-day forecast, coordinates or airport, °C and °F, with named data sources. An agent immediately knows what it returns. However, it never distinguishes itself from the sibling get_airport_forecast despite accepting an 'airport' parameter, leaving overlap unresolved.

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 only implied — 'weather anywhere' suggests it is the general-purpose weather tool, but there is no explicit when-to-use guidance and no mention of when to prefer get_airport_forecast, get_airport_status, or check_trip_delay_risk. Alternatives in the sibling list go unaddressed.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuine context beyond them: it discloses what a result row contains, and that short-duration crypto markets are deliberately excluded — a non-obvious filtering behavior the agent could not derive from 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?

Three short sentences, front-loaded with what the tool returns, then the exclusion rule, then the complementary call. No filler or restated boilerplate; every sentence 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?

With an output schema present, the description needn't explain return values, and annotations cover the safety profile, so the remaining burden is scoping and routing — both partly addressed. The one gap is the absence of a direct pointer to the skilled/smart-money sibling tools for filtered whale lists.

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

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

Schema description coverage is 100% for both params ('min' = minimum trade size USD, 'limit' = 1-50 trades), so the schema already carries the semantics. The description's 'above a size you choose' loosely restates 'min' but adds no format or default detail, so baseline 3 applies.

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

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

States a specific verb+resource: largest recent buys and sells across all Polymarket markets above a user-chosen size, and enumerates the returned fields. It implicitly distinguishes itself from the sibling get_skilled_whale_trades by noting it covers 'all markets' and that judging whether a whale is 'any good' requires a separate call, but it never names that sibling explicitly.

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?

Gives one clear scoping rule (5- and 15-minute crypto markets are filtered out) and a follow-up suggestion ('pair with /v1/wallet'), which is real guidance. However, there is no explicit when-to-use-this versus get_skilled_whale_trades or get_smart_money, leaving the agent to infer which whale-trade tool fits a given query.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds useful content context (daily freshness, spread and inversion coverage) and a 'not investment advice' disclaimer, but says nothing about rate limits, caching, or data provenance.

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 with the resource front-loaded and every clause carrying distinct data content. No filler, no 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?

With no parameters, full annotation coverage, and an output schema present, the description's job is mainly to frame the data. It does that well by listing the fields, though the enumerated return contents partially duplicate the output schema and omit any note on data source or update cadence.

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, which is the baseline-4 case. There are no parameter semantics for the description to clarify, and nothing misleading is stated.

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 (U.S. Treasury yield curve) and enumerates its contents — daily yields from 1M to 30Y, 10Y-2Y and 10Y-3M spreads, inversion flags. This is clearly distinct from siblings like get_exchange_rates or get_oil_prices, though it never explicitly contrasts itself with them.

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 when-to-use statement or exclusion of alternatives, but the tool is a zero-parameter single-purpose data fetch, so the usage context (retrieve current Treasury curve data) is strongly implied. No routing guidance between this and other macro/rate tools is offered.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds provenance (Wikipedia input, Polymarket universe, x402Pulse scoring) and a "not investment advice" disclaimer, which is useful framing. It does not disclose pagination, freshness, or rate behavior, so it remains a modest add over the annotations.

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

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

Front-loads the composite value proposition, then a usage line, then a disclaimer. Mostly efficient, though "Find markets the public is suddenly paying attention to" partially repeats the opening sentence and the framing borders on marketing prose. Generally tight and well-ordered.

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?

An output schema exists, so return-shape detail is not the description's burden, and the two optional params are fully documented in the schema. The description covers what the tool returns conceptually and its data sources. The remaining gap is routing against near-duplicate siblings, which prevents a 5.

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% (both lang and limit documented, including the 1-10 range), so the schema does the heavy lifting. The description says nothing about either parameter, adding no meaning beyond structured fields. Baseline 3 applies when the schema fully documents parameters.

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 a specific composite resource: Wikipedia trending/spiking topics joined to open Polymarket markets, with prices and a skilled-trader lean. The verb (list) and the intersection it covers are clear enough to distinguish it from adjacent siblings like list_trending_topics or get_topic_attention. It stops short of explicitly naming which sibling to prefer when, so it is not 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?

"Find markets the public is suddenly paying attention to" implies a usage scenario, which is better than nothing. However, with many closely related siblings (list_attention_spikes, get_topic_attention, list_trending_topics, find_market_disagreements) there is no explicit when-to-use, when-not-to-use, or alternative routing. Usage is implied rather than 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?

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description adds meaningful context beyond them: the 'yesterday' time window, the ratio-to-median metric, automated-traffic filtering, and the Wikimedia/CC0 data source.

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 leads with the resource name and then layers definition, metric, time window, and provenance without filler. Slightly dense but every clause 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?

With an output schema present, return values need not be described, and annotations carry the safety profile. The description covers concept, metric, time window, and data source; only explicit usage/alternative guidance 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 description coverage is 100%, so the schema already documents lang, limit, minRatio, and minViews. The description adds no parameter syntax or format detail beyond that, which is the expected baseline when the schema does the heavy lifting.

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 a specific verb (list) and resource (attention spikes) and defines the concept precisely: Wikipedia articles whose views surged above their previous week's median. It stops short of explicitly distinguishing itself from close siblings like get_topic_attention or list_trending_topics, so an agent must infer 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?

It hints at value ('earliest sign of breaking public interest'), implying a use case, but gives no explicit when-to-use or when-not guidance and never names an alternative. The agent gets no help choosing between this and the several other attention/topic siblings.

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

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world. The description adds useful context that results are 'decoded and ranked' and include a link to the filing, plus a non-advisory disclaimer. It does not disclose ranking criteria, pagination, or auth/rate-limit behavior, so it adds modest value over the structured hints.

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

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

Front-loaded with the core purpose, then a dense but useful enumeration of event types. Single sentence plus a short disclaimer; no filler, though the event list is lengthy.

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

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

With an output schema present, the description need not explain return values, and annotations carry the safety profile. Scope and covered event types are well explained; only explicit sibling-routing guidance is missing 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?

Schema coverage is 100%, and the schema documents both 'ticker' and the 'days' range (7 to 365). The description adds no parameter syntax or defaulting details beyond what the schema provides, making the baseline 3 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?

States a specific verb and resource (lists material corporate events from SEC 8-K filings) and enumerates the exact event types covered, so the agent knows what it will receive. This is clearly distinguishable from siblings like get_company_financials or get_company_brief.

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 purpose implies when to use it (surfacing material 8-K events for a company), but there is no explicit comparison or routing guidance against siblings such as get_company_brief, get_company_financials, or list_insider_trades. No exclusions or prerequisites 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds useful provenance (annual financial disclosures, self-reported values) and a 'facts, not investment advice' disclaimer, but says nothing about data recency, staleness of disclosures, or how limit behaves beyond 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?

A single dense sentence with the resource and both modes front-loaded before the disclaimer. Slightly overpacked but every clause carries information; no filler.

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

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

Only two optional parameters, both fully described, and an output schema exists so return values need not be explained. The description covers both invocation modes and the data source, leaving nothing an agent needs missing.

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

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

Schema coverage is 100%, so both parameters are fully documented with an example ticker and the semantics of omitting it. The description restates the same dual-mode meaning for ticker without adding format or validation detail; baseline 3 is appropriate.

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

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

States a specific verb+resource (congressional stock holdings from annual financial disclosures) and describes both output modes. It implicitly distinguishes holdings from trading activity, but never names the obvious sibling list_congress_trades, so an agent must infer the distinction.

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

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

Gives clear conditional usage: with a ticker you get which members hold it and reported values, without one you get the most-held stocks. No explicit exclusions or pointer to alternatives such as list_congress_trades, so routing between the two congress tools is left to 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?

Annotations already cover read-only, idempotent, non-destructive, open-world behavior, so the description's job is supplemental. It adds real value: the data source (STOCK Act disclosures), the derived fields (late-disclosure flag, performance vs. S&P 500), and a compliance framing ("Facts, not investment advice"). It omits pagination/limit behavior and the freshness or latency of disclosure data.

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?

Front-loaded with the core resource and scope, then the two access modes, then a short disclaimer. The long field enumeration in the parenthetical is dense but earns its place by signaling the returns; nothing is filler, though the list could be tightened.

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 a full output schema, the description needn't explain return values, and annotations carry the safety profile. What remains — source, scope, ticker vs. aggregate mode, filtering options, and the not-advice caveat — is all present, so an agent can call this correctly without further probing.

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

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

Schema coverage is 100%, so the baseline is 3. The description clarifies the ticker-vs-no-ticker tradeoff (full history vs. latest across Congress), but that is largely duplicated by the schema text, and it never explains what the `days` window actually measures or how `limit` truncates results.

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 a specific resource and origin (stock trades by members of Congress from House/Senate STOCK Act disclosures) and enumerates the returned fields, so the agent knows exactly what data it gets. It does not explicitly differentiate itself from the close sibling list_congress_holdings (holdings vs. transactions), leaving that distinction to inference.

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?

"By ticker (full history) or across Congress (latest), filter by member or chamber" gives clear context for the two main calling modes. It never states when to use a sibling instead (e.g., get_congress_member for member profiles, list_congress_holdings for portfolios) or any exclusions, so it stops short of full routing guidance.

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

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the bar is lower. The description still adds real context: the data source (federal lobbying disclosure reports), what the untickered call returns, and an explicit 'facts, not investment advice' framing. It stops short of noting freshness/lag or how the days window interacts with the aggregation.

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 front-loaded with the resource and what it returns, followed by the fallback case and source. No filler, no 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?

An output schema exists, so return-value description is unnecessary, and the description covers source, scope, and the untickered default. The remaining gap is the temporal dimension — no default or interpretation for days, and no indication of how limit affects results — which matters for a time-windowed disclosure query.

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

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

Schema coverage is 100%, so the schema already documents days (1-1095), limit (1-100), and ticker. The description only restates the ticker's optionality and omits what the days window measures (reporting period vs. filing date) and what the limit caps, so it adds little beyond structured fields. Baseline 3 is appropriate.

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

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

States a specific resource (corporate lobbying disclosure) and enumerates exactly what is returned: spend amounts, issues and bills, and the firms used. The fallback behavior ('without a ticker, the biggest corporate spenders') further sharpens the contract, and it is clearly distinct from siblings like list_pac_donations and list_revolving_door_lobbyists.

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 implies when the tool is appropriate ('what a company reported spending on lobbying') and documents the parameter-dependent default (all companies / top spenders without a ticker). But it never routes the agent away from near-neighbors such as list_pac_donations or list_revolving_door_lobbyists, nor states any prerequisite or exclusion.

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

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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld, so the safety profile is covered. The description adds the provenance (Drugs@FDA) and the novel-drug/NME flag, which is useful, but says nothing about defaults, page sizes, or result caps.

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 passage that front-loads what it returns and then lists fields and filters without filler. The field enumeration is long but each item is meaningful.

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 a full output schema and rich annotations, the return shape and safety profile are already covered, so the description only needs to frame scope — which it does. Minor gap: no stated default for the days window or result limit.

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

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

Schema coverage is 100%, so the schema already documents all four parameters. The description restates the sponsor, days, and original-vs-supplemental filters but adds no syntax or format detail beyond the schema, and omits limit entirely. 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?

States a specific verb (list) and resource (FDA drug approvals), plus the exact source (Drugs@FDA) and content types (new drugs, generics, biologics). This clearly separates it from neighbors like list_fda_recalls, get_drug_label, and get_drug_safety.

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 frames the use case ('which companies just won FDA approval') and names the filter dimensions, implying usage, but never says when to prefer this over sibling tools like list_fda_recalls or get_drug_safety, and offers no exclusions.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description still adds real value by citing the data source (openFDA), the aggregation model (grouped by drug), and a scope disclaimer ('not medical advice'), none of which are in the structured fields.

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?

Front-loaded with the resource, then a compact second sentence covering modes and audience. The opening sentence is a long enumerative list but each clause describes a distinct returned field, so it earns its space without bloat.

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?

An output schema exists, so return values need not be re-explained, and all three parameters are documented in the schema. The description supplies source provenance and a usage disclaimer, leaving only minor gaps such as the absence of any mention of result count/paging 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?

Schema description coverage is 100%, so the baseline is 3. The description loosely maps to the parameters ('search one drug' -> drug, 'current shortages' -> status) but adds no format or syntax detail beyond what the schema already provides for drug, limit, and status.

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 a specific verb and resource (FDA drug shortages) and adds unusual detail about what it surfaces: availability per package, companies, dosage forms, reasons, recovery notes, and posting dates. This content makes it clearly distinct in substance from list_drug_approvals and list_fda_recalls, though it never names or contrasts those siblings explicitly.

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?

'Search one drug or list current shortages' sketches the two modes and 'For hospitals, pharmacies and supply chains' names an audience, but there is no guidance on when to choose this over adjacent tools like list_drug_approvals or get_drug_label, and no exclusions.

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

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description usefully adds the data provenance ('openFDA data') and an interpretation aid ('Class I is most serious') plus a 'not medical advice' disclaimer. It does not address result limits or pagination, so it adds moderate value beyond structured fields.

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 then a short disclaimer; the resource and returned fields are front-loaded with no filler. Slight overlap with the title ('FDA drug recalls and food recalls') costs a point but the structure is otherwise 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?

An output schema exists, so return-value documentation is not required, and annotations cover the safety profile. The description supplies domain context (source, class severity, disclaimer) and filter intent; the only minor gap is the absence of any note on result limits despite a 'limit' parameter.

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 schema already documents all five parameters, and the description merely restates the filterable dimensions (class, company, time window). The 'Class I is most serious' note adds interpretive meaning for the class enum but nothing beyond that. Baseline 3 is appropriate.

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

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

The description names a specific resource (FDA enforcement reports for drug and food recalls) and enumerates the returned fields (recall class, firm, product, reason, status, dates, distribution). It clearly separates this from siblings like list_drug_approvals, list_drug_shortages, and detect_drug_safety_signals, which cover different domains.

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 states which filters are available ('Filter by class, company and time window'), implying the usage context, but never says when to prefer this tool over alternatives or what conditions select it. No exclusions or sibling routing are given.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description adds real behavioral context beyond them: results are ranked by severity, reasons are in plain language, and private-aircraft-only restrictions are segregated, which prevents a concrete misreporting failure mode.

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 scope and ranking, the second handles the misuse caveat and exclusions. No filler, no repetition of the title or annotations.

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?

An output schema exists, so return-format details are unnecessary. Given a zero-required-parameter listing tool, the description covers scope, normalization (severity ranking, plain-language reasons), a data-quality caveat, and an explicit exclusion — everything an agent needs to invoke and interpret it.

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

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

Schema coverage is 100%, but the schema only says the single parameter is "true or false" with no explanation of its effect. The description supplies that missing meaning by explaining that private-aircraft-only restrictions are separated out, which is what the flag plausibly governs, adding value over the schema's label-only text.

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 a specific verb and resource (every current FAA disruption in U.S. airspace) and enumerates the concrete types covered: ground stops, ground delay programs, arrival/departure delays, airspace flow programs, and real closures. This clearly distinguishes it from siblings like get_airport_status or get_airport_forecast without needing their schemas.

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

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

Explicitly states a when-not boundary ("Not for flight planning") and warns about a common misuse (private-aircraft-only restrictions must not be reported as closures). It does not, however, name a sibling alternative for the flight-planning use case, so routing to the right tool is still partly inferential.

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

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

Annotations already cover safety traits (read-only, idempotent, non-destructive, open-world), and the description adds useful context: the data comes from 13F filings, covers the latest quarter, and includes a 'not investment advice' caveat. It does not disclose filing lag, update cadence, or coverage limitations, but it meaningfully supplements the annotations.

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

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

The description is front-loaded with the core purpose and then efficiently enumerates stock, fund, and default modes. It is dense but every clause contributes useful scope or caveat information.

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

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

Given the output schema exists and the input schema is fully documented, the description provides enough context to invoke the tool correctly. It could be stronger with explicit sibling routing, but no critical invocation detail is missing.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds mode semantics beyond the schema: ticker drives stock-level results, fund drives fund-level results, and neither drives market-wide results. It does not expand on limit behavior beyond the schema's '1 to 100'.

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 origin: hedge fund/institutional moves from 13F filings, with stock-level, fund-level, and market-wide modes. It is clear what the tool returns, but it does not explicitly distinguish itself from sibling tools such as get_smart_money, get_whale_trades, or list_top_shareholders.

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 clearly explains the three invocation modes: pass a ticker for a stock, pass fund= for a specific fund, or omit both for market-wide biggest moves. It does not state when to prefer this tool over sibling alternatives, so it falls short of full when/when-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?

Annotations already disclose readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by naming returned fields, noting totals and cross-company top recipients, and clarifying that results are facts rather than investment advice. It does not cover freshness or pagination, but the annotations and output schema carry much of that burden.

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 resource and returned fields come first, followed by filtering scope and a brief disclaimer. Every sentence carries useful information with no redundant filler.

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

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

Given the rich annotations, 100% schema description coverage, and presence of an output schema, the description provides enough context for an agent to select and invoke the tool correctly. It states the domain, returned data, filtering options, and scope without needing to duplicate structured details.

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 all four parameters are already documented in the input schema. The description reinforces ticker and minimum-size filtering but does not add new semantics for days or limit beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 federal government contract awards to public companies and lists the returned fields (agency, amount obligated, purpose, dates, totals, top recipients). It is specific enough to distinguish from unrelated siblings such as list_congress_trades or list_corporate_lobbying, though it does not explicitly name a direct alternative.

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 filtering modes — 'By ticker or across the market, with a minimum size' — which implies how to use the tool. However, it does not explicitly state when to use this tool versus siblings or any exclusions, leaving usage guidance implicit 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?

Annotations already cover read-only, idempotent, open-world, non-destructive, so the safety bar is low; the description still adds real substance by disclosing that results are the *largest* filings (implicitly size-ranked), that a default minimum value threshold applies via minUsd, what a 'cluster buy' means (3+ insiders buying the same stock), and that returned fields include insider, role, shares, price and value. It omits pagination, result-cap behavior and freshness/latency, which keeps it below a 5.

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 leads with the resource and then enumerates scope, fields and cluster-buy semantics; there is little waste. The disclaimer 'Data, not investment advice' is defensible for a financial feed, but the sentence runs long and mixes return-field inventory with selection criteria, which slightly dilutes scanability.

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?

An output schema exists, so return-value shape need not be explained, and annotations cover the safety profile; the description fills the remaining gap by defining selection criteria (largest, open-market, lookback, optional ticker, cluster definition). The one material gap is the absence of any contrast with list_insider_trades, which is exactly the ambiguity an agent would hit next.

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 nominally 100%, but the schema descriptions are bare ranges ('1 to 90', '1 to 100') that convey no meaning; the description compensates by establishing that 'days' is a lookback window over filings and that 'ticker' is an optional narrowing filter (without it: all stocks). It does not clarify units or interaction between limit and minUsd beyond what the schema states, so it improves on the baseline rather than fully covering it.

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

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

Names a concrete resource and scope: the largest open-market insider purchases and sales across all U.S. stocks in a lookback window, optionally narrowed to one ticker, plus cluster-buy detection. That is far more specific than a restatement of the name. However, it never distinguishes itself from the sibling tool list_insider_trades, leaving the agent unable to choose between two near-identical insider-data tools from the description alone.

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 only implied: the parenthetical '(or for one ticker)' tells the agent how to narrow the feed and 'in the last days' implies a recency-bounded use case. There is no explicit when-to-use/when-not guidance and no pointer to list_insider_trades or get_smart_money as alternatives. On a tool list containing a directly overlapping sibling, that omission costs it a point.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, covering the safety and side-effect profile. The description adds data-shape context (10b5-1 flags, cluster-buy detection) but this largely duplicates what the output schema would express, and it says nothing about rate limits or pagination behavior. With annotations and an output schema present, this is an adequate but not additive description.

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 names the resource and source, followed by a brief disclaimer. The field enumeration is somewhat list-like but every element maps to real returned data, and there is no filler. Minor trimming possible, but it is well structured.

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

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

With 100% schema coverage, full annotations, and an output schema, the description only needs to frame the tool's domain, which it does. The absence of usage/routing guidance is the one gap, but overall the agent has enough 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 100%, so the schema already documents ticker, days, limit, and openMarketOnly. The description mentions none of these parameters and adds no syntax or constraint detail beyond the schema. Baseline 3 applies when structured fields carry the burden.

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 (insider trades) and its source (SEC Form 4 filings), so an agent can tell what the tool returns. It does not explicitly differentiate from siblings, but none of the listed siblings cover insider trades, so confusion risk is low. The phrasing leans toward enumerating output fields rather than stating the action, 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?

There is no guidance on when to call this tool, when not to, or what alternative to prefer for related data (e.g., get_whale_trades or get_smart_money). 'Data, not investment advice' is a disclaimer, not usage guidance. The agent is left to infer the appropriate context.

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

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

Annotations already cover readOnly, idempotent, non-destructive, and openWorld. The description adds real value on top: it discloses the source platform (Polymarket), the derived metric (skill-weighted money vs. market odds) and its provenance (x402Pulse scoring), plus a non-advisory disclaimer.

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?

One dense but front-loaded sentence plus a short disclaimer; the core resource and payload are stated before the qualifying detail. Slightly heavy with stacked parentheticals, but nothing is wasted.

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?

An output schema exists, so return-value explanation is unnecessary, and the description still characterizes the key field. It is complete for invocation; only the lack of routing guidance against sibling list/smart-money tools keeps it from a 5.

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

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

Schema coverage is 100% with a single 'limit' parameter ('1 to 10'), so the schema does the documenting work. The description contributes no additional parameter semantics, which is the correct baseline when coverage is high.

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 (busy Polymarket prediction markets about oil prices, OPEC, Strait of Hormuz, fuel) and the distinctive payload (skill-weighted money lean from x402Pulse scoring). This domain framing clearly separates it from siblings like list_attention_markets, get_oil_prices, and get_smart_money.

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?

Scope implies usage (query when oil-related prediction-market sentiment is wanted) and the 'busy' qualifier hints at a filtered subset, but no explicit when-to-use or alternative routing (e.g., vs list_attention_markets or get_oil_prices) is given. Only the 'Data, not trading advice' caveat sets any boundary.

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

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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered; the description adds real value on top by naming the data provenance (federal campaign finance filings) and the derived flagging behavior for sitting members of Congress. It stops short of disclosing pagination/truncation behavior relative to the limit parameter.

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 a colon-delimited inventory of what the tool returns, plus a short compliance note. Every clause contributes content; there is no filler or restatement 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?

With an output schema present, the description need not explain return shapes, and it already enumerates the categories of data returned and their source. Moderate gap: it never states the default time window or result cap despite those parameters driving the scope of a filing-based list.

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

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

Schema coverage is 100%, so all three parameters are documented in the schema, and the description adds nothing about days, limit, or how the ticker maps to a PAC. The schema's own descriptions are terse numeric ranges ('1 to 1095'), but with full coverage the baseline of 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 names a specific resource (a company's employee PAC political contributions from federal campaign finance filings) and itemizes the returned content: totals, refunds, top recipients, individual contributions, and a sitting-Congress flag. That is far more specific than the bare name and clearly separates it from siblings like list_congress_trades or list_corporate_lobbying.

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 statement of when to choose this tool over list_corporate_lobbying, list_congress_holdings, or get_company_brief, and no prerequisites or exclusions. The trailing line 'Facts, not investment advice' is a disclaimer rather than usage guidance, so an agent must infer the selection context from the ticker parameter alone.

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

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

Annotations already declare read-only, idempotent, open-world, and non-destructive behavior. The description adds the useful framing 'Facts, not accusations' and lists returned fields, but does not disclose deeper behavioral details such as freshness, limitations, or pagination.

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, defining the resource first and then clarifying scope. Every sentence contributes without unnecessary 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?

Output schema and annotations carry much of the structural burden, and the description supplies the conceptual definition and ticker/market scope. It is nearly complete, though it does not mention the time-window parameter or result limits explicitly.

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 all three parameters are already documented in the schema. The description only reinforces the ticker scope and does not add meaning for days or limit beyond what the schema provides.

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

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

The description clearly defines the specific resource: people who moved from government jobs into lobbying, including the data fields returned. It is more specific than the name alone, but it does not explicitly differentiate this from sibling tools such as list_corporate_lobbying.

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 states the tool can be used 'By ticker or across the market,' which clarifies optional ticker usage. However, it gives no explicit guidance on when to choose this tool versus alternatives like list_corporate_lobbying or list_congress_trades.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds genuine behavioral context with 'plus the largest option holders when reported' — disclosing that some sections are conditionally present — but says nothing about data freshness (e.g., filing period) or result ordering, which matters for a holdings snapshot.

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 enumerates the payload contents without filler, and the disclaimer is short. Nothing is redundant, though the trailing legal disclaimer is marginally off-task for an agent deciding how to call the tool.

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 read-only tool with an output schema (so return shape needn't be explained) and full annotation coverage, the description supplies everything needed: resource, holder categories, included fields, and the conditional nature of option-holder data.

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 both the ticker format (AAPL) and the limit range (1 to 100) are already documented in the schema. The description adds nothing about parameter meaning, 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?

States a specific verb+resource (largest shareholders of a company) and enumerates the holder categories returned (institutions, insiders/individuals, option holders), so an agent knows exactly what content to expect. It does not, however, distinguish itself from adjacent tools such as list_insider_trades, get_whale_trades, or get_company_brief, which an agent may consider as substitutes.

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 when-to-use or when-not-to-use guidance, and no alternatives are named. The closest thing is the disclaimer 'Data, not investment advice,' which frames intent but does not route the agent between this tool and its many sibling ownership/insider tools.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond that: the ranking inputs (edge over odds, return, consistency) and the notable claim that it surfaces big-volume losers a profit leaderboard would hide. Caching or rate-limit behavior is not mentioned, but with annotations present the bar is lower.

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 core differentiator ('re-ranked by skill, not size') is front-loaded and the whole definition is a single dense sentence with little waste. The stacked parentheticals (periods, then categories) make it slightly heavy for a leaderboard-list tool, but it remains 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?

An output schema exists, so return values need not be explained, and annotations carry the safety profile. For a read-only ranked-list tool with three optional, fully documented parameters, the description supplies enough conceptual context (what ranking means, the periods/categories available) for an agent to call 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 100% with all 3 optional parameters (limit, period, category) fully documented, including enum values and the default of 'month'. The description largely reiterates the same periods and categories, adding no syntax or format detail beyond the schema, so the baseline 3 is appropriate.

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

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

The description gives a specific verb+resource with scope: ranks top traders by edge over odds paid, return and consistency, across periods and categories. It conceptually distinguishes itself from a plain profit leaderboard ('re-ranked by skill, not size'), but never names or contrasts against actual siblings like get_smart_money or get_skilled_whale_trades, leaving some ambiguity among the many trader-related 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?

It conveys the ranking philosophy and the available periods/categories, which implies when the tool is relevant (skill over raw volume). However, it offers no explicit when-to-use or when-not-to-use guidance versus get_whale_trades, get_smart_money, or get_skilled_whale_trades, so an agent must infer which trader tool applies.

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