supply-chain-intelligence

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

With no annotations, the description carries the full disclosure burden. It provides useful behavioral context: coverage of 31 commodities across multiple categories, return value (current price and 24-hour change percentage), and free/paid tier limitations. It does not explicitly state read-only status or rate limits, but the monitoring nature implies read-only, and the tier details add transparency beyond a minimal 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?

The description is well-structured and front-loaded with the core purpose. It lists commodity categories in a clear, parseable format without unnecessary verbosity. Every sentence provides useful information: the main function, the coverage, the output, and tier constraints. It is concise given the breadth of information conveyed.

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

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

Given the tool has no parameters and no output schema, the description effectively explains what the user can expect: current price and 24-hour change percentage. It also covers tier limitations and the full commodity list. It lacks details like data source or update frequency, but these are not essential for basic invocation and are compensated by the clear output description.

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

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

The tool has zero parameters, and the schema is empty. The baseline for 0 parameters is 4. The description adds meaning by explaining that all commodities are tracked without needing a parameter, clarifying that the tool returns global data for a fixed set of commodities. No further parameter documentation is necessary.

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

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

The description clearly states the tool monitors real-time commodity prices and price volatility, with an explicit resource list of 31 commodities. It distinguishes itself from sibling tools like get_commodity_volatility_alerts by specifying the return of current price and 24-hour change percentage, making the purpose specific and non-overlapping.

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

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

The description gives a clear context ('for supply chain cost management') but does not explicitly state when to use this tool versus alternatives. There is no mention of when not to use it or how it compares to related tools such as get_commodity_volatility_alerts. The use case is implied rather than explicitly differentiated.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains the statistical validation (p≤0.01), output statuses, and access restriction ('Paid tier only'). However, it does not mention potential error conditions, rate limits, or whether results are cached, leaving some gaps.

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

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

The description is three concise sentences, each adding essential information: the action and data sources, the methodology and quality metrics, and the output format plus access level. There is no fluff or repetition, and it is front-loaded with the primary purpose.

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

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

For a tool with no parameters and no output schema, the description sufficiently covers what it does, how it works, and what it returns. The mention of 'live GDI and SMI data' and 'Paid tier only' adds necessary context. It could elaborate on edge cases (e.g., empty results), but overall it is complete for its complexity.

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

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

The tool has zero parameters, so parameter semantics are trivially satisfied. The baseline for 0 params is 4, and since the description doesn't need to explain inputs, it correctly omits them. No additional parameter-related value is required.

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

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

The description uses a specific verb ('Get') and clearly identifies the resource: 'statistically validated leading indicator signals evaluated against live GDI and SMI data.' It further distinguishes itself from siblings by detailing the Granger-causal methodology (p≤0.01) and the return statuses (ACTIVE, WATCH, CLEAR), making the tool's unique purpose unambiguous.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives. It mentions 'Paid tier only' as a prerequisite but does not state use cases, exclusions, or when to choose another sibling tool like get_predictive_signals. The usage context is only implied by the tool's name and description.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It is quite transparent: it describes the return payload (FAA ground delays, arrival/departure delays, closure status, disruption score, traffic collapse detection) and the geographic scope. It lacks details on update frequency or potential error/empty-result behavior, but for a no-param read-only tool, this is adequate.

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 four sentences, each serving a distinct purpose: scope, return data, covered airports, and target users. There is no redundancy or filler. It is front-loaded with the core purpose and then provides necessary detail efficiently.

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

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

Given the tool has no parameters, no output schema, and no annotations, the description must stand alone. It covers what the tool does, what data it returns, where it applies, and who uses it. This is a complete picture for a no-param data retrieval tool.

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

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

The tool has zero parameters, so the baseline for this dimension is 4. The description does not need to clarify parameter semantics; the schema is trivial (empty properties). No additional parameter information could be added that would meaningfully improve the description.

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

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

The description clearly states the tool's function with a specific verb and resource: 'Get real-time air cargo disruption status at major US and international freight hub airports.' It lists the exact types of data returned (FAA delays, ground stops, etc.) and names key airports, making it easy to distinguish from sibling tools like rail or port status tools.

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

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

The description provides clear context for when to use this tool: 'Used by air freight forwarders, express carriers, and logistics planners to reroute time-sensitive shipments around airport disruptions.' It implies that this is the go-to for air cargo disruptions, but it stops short of explicitly stating when NOT to use it or naming alternatives for other transport modes.

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

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

With no annotations provided, the description carries the full burden. It discloses the update frequency ('Updated every 30 minutes from US Customs and Border Protection'), the data returned (delay in minutes, lanes open, port status), and coverage scope. This provides useful behavioral context beyond mere 'get data' and helps set expectations, though it omits any error/availability details.

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

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

The description is a compact three-sentence paragraph that front-loads the primary purpose, then adds data details and use cases. It is efficient, but includes a long list of port examples that, while useful, could be trimmed for strict minimalism.

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

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

For a simple no-parameter tool with no output schema, the description fully covers what it does, what data it returns, how fresh the data is, geographic scope, and typical use cases. It is complete and self-contained.

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

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

The tool has zero parameters, and the baseline for 0 parameters is 4. Since there is no input schema to clarify, the description doesn't need to explain parameters, but it does adequate context for how the tool is invoked (no arguments needed).

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

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

The description clearly states the tool's function with a specific verb and resource: 'Get real-time commercial border crossing wait times at US-Mexico and US-Canada ports of entry.' It distinguishes this from siblings like port congestion monitors by focusing specifically on border crossing delays and commercial vehicles. This is a precise, distinctive 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?

The description provides clear context for when to use the tool, noting it is 'Used by logistics companies, freight brokers, and trucking operations to route cross-border shipments through the fastest crossing points.' However, it does not explicitly mention when not to use it or compare with alternative sibling tools, so it falls slightly short of a perfect score.

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

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

With no annotations, the description carries the full burden and does well: it discloses the specific return fields (vessel count, average speed, slow/stationary count, congestion score) and explains the real-time signal. It lacks operational caveats (e.g., update frequency), but for a no-parameter read-only tool, it is reasonably transparent.

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

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

The description is three sentences: purpose and scope, return values, and domain significance. Every sentence adds value, is front-loaded, and avoids fluff. It is concise yet informative.

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

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

The description explains what the tool returns and why it matters, including the rerouting signal. It does not detail the exact units or time coverage, but for a simple snapshot tool with no output schema, it is sufficiently complete.

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

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

The tool has zero parameters, so the baseline is 4. The description does not need to elaborate on parameter syntax or meaning; it instead focuses on the output, which is appropriate.

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

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

The description clearly states the tool monitors real-time vessel traffic and congestion at critical maritime chokepoints, listing specific examples (Suez, Panama, Malacca, etc.). This specific verb-resource pairing distinguishes it from general port congestion tools and other siblings.

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

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

The description provides a clear use case: detecting chokepoint congestion or closures and the resulting rerouting signal. It does not explicitly name alternatives or state when not to use it, but the context is strong enough to guide selection.

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

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It explains the detection criteria (24-hour price change exceeds normal ranges or extreme levels) and the returned fields (current price, 24-hour change percentage, trend direction, risk assessment). This is transparent about what the tool does, though it does not detail edge cases or limitations.

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 in the first sentence. It includes some fluff ('a question that takes procurement teams hours to answer manually') but remains efficient overall. The three sentences cover purpose, behavior, and target users without excessive 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?

Given the tool's simplicity (no parameters, no annotations, no output schema), the description is remarkably complete. It covers the tool's purpose, detection criteria, returned data, and primary use cases, fully meeting the contextual needs for an agent to decide to invoke 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?

The tool has zero parameters, so the baseline for parameter semantics is 4. The description adds no parameter-related information because none is needed; schema coverage is trivially complete.

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 specifies the tool's function: getting alerts for commodities with abnormal price volatility. It distinguishes itself from siblings like commodity_price_monitor by focusing on anomalous behavior (volatility alerts), not general price monitoring.

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

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

The description gives clear usage context: it answers 'which commodities are behaving unusually right now?' and lists specific audiences (procurement teams, commodity traders, supply chain managers). It does not explicitly mention when not to use it or name alternatives, but the context is sufficient.

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

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

With no annotations, the description explains the scoring methodology (weakest link, combining real-time port congestion and active natural disaster proximity) and the scope of 10 corridors. This goes beyond a simple 'monitor' phrase and gives behavioral insight, though it does not explicitly state the output format or that it is read-only.

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

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

The description is three sentences long and packs in valuable detail: corridor list, scoring logic, and target users. It is information-dense without being verbose, though the corridor list could be considered slightly niche; still, 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?

Despite lacking an output schema, the description gives sufficient context about the tool's operation and expected use cases. The only minor gap is not specifying the exact return format, but for a zero-parameter monitoring tool, this is acceptable.

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

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

The tool has zero parameters, so the description has nothing to add beyond the empty input schema. The baseline of 4 applies because parameter documentation is unnecessary, and the description does not incorrectly mention any 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?

The description clearly states the tool's function: monitoring risk levels across 10 specific ocean freight corridors. It lists the corridors and explains the scoring mechanism (weakest link, combining port congestion and natural disaster proximity), which distinguishes it from sibling tools like port congestion monitor or natural disaster alerts.

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

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

The description provides explicit use cases for logistics planners, procurement teams, and freight forwarders, indicating clear scenarios for use. However, it does not mention when not to use the tool or name alternative tools, so it falls short of full 5-level guidance.

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

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

With no annotations, the description carries the transparency burden and does disclose useful details like the 55/45 weighting, 21-country coverage, higher-score-means-more-friction, and 30-day history for country detail. However, it claims an optional country parameter that does not exist in the schema, which is misleading and undermines trust. It also doesn't mention data sources or update frequency.

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 four sentences and front-loads the core purpose and key facts. The weighting, coverage, and interpretation details are all relevant and non-redundant. The final sentence about target users adds context but is slightly expendable, keeping it from a perfect score.

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

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

Given there is no output schema and no annotations, the description covers the essential purpose, composite calculation, geographic scope, and score interpretation. The phantom country parameter and the lack of explicit guidance on when to use this tool versus related siblings are notable gaps. It also doesn't clarify what the aggregate response format looks like without a country selector.

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

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

The input schema has zero properties, so the baseline for 0 params is 4, but the description explicitly mentions an 'Optional country parameter' that is not represented in the schema. This is a direct contradiction and will lead an agent to attempt passing a parameter that will fail validation. The description should not invent parameters absent from 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 starts with a specific verb+resource: 'Get customs friction baseline scores by country.' It explains the composite 0-100 score and weights, clearly distinguishing it from sibling tools like get_customs_trade_events or get_port_congestion_trends by highlighting its combined nature.

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

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

The description provides clear context by stating the tool is used by trade compliance teams, procurement managers, and logistics planners to assess customs clearance risk. It doesn't explicitly name alternatives or when-not-to-use, but the composite score definition implies its role relative to more specialized 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?

With no annotations, the description carries the full burden. It discloses the data source and the fields included in each event, but does not mention update frequency, response format, or limitations. The behavior is partially transparent but lacks some operational details.

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

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

The description is three sentences, each serving a distinct purpose: function, coverage, and data fields with audience. It is efficient and front-loaded, with no redundancy.

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

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

For a zero-parameter tool without an output schema, the description covers purpose, content, and use case well. The only minor gap is not explicitly stating whether the tool returns a list or a single event, though 'events' implies a 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?

The tool has zero parameters and the schema coverage is 100%, so the baseline is 4. The description adds valuable context about the data structure (direction, US impact, confidence score), which enriches the agent's understanding of what the tool returns.

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

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

The description clearly states the tool retrieves customs and trade policy events from news intelligence, with specific coverage (tariff changes, sanctions, etc.). It distinguishes itself from siblings like get_trade_policy_impacts by detailing the event-level data and target audience.

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

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

The description provides clear usage context by stating it is used by trade compliance teams and procurement managers to track policy risk. It does not explicitly mention exclusions or alternatives, but the use case is specific enough to guide selection among sibling tools.

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

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

With no annotations, the description carries the full burden for behavioral disclosure. It adds valuable context by listing data sources, mentioning 'Events auto-expire based on source TTL,' and describing filtering capabilities. It does not explicitly state read-only behavior or rate limits, but the 'Get' verb and the described mechanics give reasonable transparency.

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

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

The description is efficiently packed into four sentences, each earning its place. It starts with the main purpose, then adds sources, output fields, TTL behavior, filtering, and sibling differentiation—no filler or redundancy.

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

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

Without an output schema, the description adequately lists the return fields (event type, severity, location, coordinates, affected country). It also covers sources, TTL, filtering, and the relationship to a sibling. It doesn't address pagination, rate limits, or error handling, but given the moderate complexity, this is a solid coverage.

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

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

The input schema has zero properties, leaving the description as the only source for parameter understanding. It explicitly enumerates filtering by event type, country, region, and lookback window, adding meaning beyond the empty schema. However, the lack of types or formats and the mismatch with the empty schema prevent a perfect score.

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

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

The description opens with a specific verb and resource: 'Get active natural disaster events that may impact supply chain operations.' It goes further to state sources (USGS, NOAA, GDACS) and explicitly names a complementary sibling, get_natural_disaster_alerts, which clearly distinguishes its role.

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 'Complements get_natural_disaster_alerts with additional filtering options' directly signals when to prefer this tool over a specific alternative. It also provides context via sources and return fields. However, it does not explicitly discuss exclusions or other alternatives among the many sibling tools.

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

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

With no annotations, the description carries the full burden of explaining behavior. It clearly states that the tool 'Returns' a broad set of economic data sources, which is the key behavioral trait for a read-only data retrieval tool. The absence of caveats about timing or limitations is acceptable given the simple nature of the tool, though slightly more detail could improve transparency.

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

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

The description is compact and front-loaded, with the main purpose stated in the first sentence and supporting data categories in the same sentence. The second sentence adds audience context without redundancy. Every element contributes to understanding the tool's scope and utility.

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

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

Given the tool's simplicity (no parameters, no output schema), the description covers what the tool returns (specific indices and forecasts) and who should use it. The data source enumeration provides enough context for an agent to know whether this tool fits a request for macro-economic supply chain indicators.

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

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

The tool has zero parameters, and the schema is empty. The baseline for zero parameters is 4, and the description appropriately does not need to explain parameter details. The description focuses on the return contents rather than inputs, which aligns with the lack of 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?

The description clearly states the tool 'Get key economic indicators affecting supply chain costs and conditions' and enumerates specific data categories (Federal Reserve data, PPI, GSCPI, EIA forecasts). This specific verb+resource+scope distinguishes it from sibling tools like commodity_price_monitor or get_energy_forecast, which focus on narrower datasets.

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 identifies target users ('supply chain strategists, procurement leaders, and economic analysts') and the intended use case ('macro backdrop for supply chain planning'). While it does not explicitly name alternatives or exclusion criteria, the context makes it clear that this is the macro-level overview tool, and siblings handle specific niches.

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

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

With no annotations, the description carries the burden. It discloses what the tool returns (a comprehensive list of data) but does not mention behavioral traits such as data freshness, update cadence, sourcing, or limitations. It accurately describes the output but lacks deeper behavioral context that an agent might need to assess reliability or side effects.

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

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

The description is longer than necessary but well-structured, beginning with the main purpose and then enumerating the data components. Each sentence provides relevant value, and the audience sentence is helpful context. It could be slightly trimmed, but it is not verbose or redundant.

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

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

For a tool with no parameters and no output schema, the description is highly complete: it explains the purpose, lists all returned data categories, and indicates target users. It lacks details on data source or refresh frequency, but given the context, it provides enough information for an agent to understand what to expect when invoking the tool.

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

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

The tool has 0 parameters and the schema is empty (100% coverage), so the baseline is 4. The description compensates by explaining exactly what data is returned, which is essential for a parameterless tool. It adds value by detailing the types of data included, making the output behavior clear without needing 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 clearly states the tool returns comprehensive US energy market status, with a specific verb and resource. It lists the data components (crude oil, natural gas, retail fuel, storage, refinery utilization, stocks, import/export flows), which establishes its purpose. It references the GDI Energy pillar and the disaggregated view, but does not explicitly contrast with siblings like get_energy_forecast, so it lacks direct sibling differentiation.

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

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

The description gives context for usage: 'for supply chain cost analysis' and identifies target users (supply chain cost analysts, transportation managers, energy procurement teams). This implies when to use the tool but does not explicitly state when to choose it over alternatives or provide any exclusions. It is clear context but lacks direct guidance on alternatives.

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

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

With no annotations, the description takes on full transparency burden. It discloses that the tool returns both historical actuals and projections, and mentions the isActual flag for distinguishing them. It does not discuss response shape or rate limits, but for a zero-parameter read-only tool, it covers the key behavioral aspects well.

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

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

The description is a single paragraph with 4-5 sentences, each providing meaningful content. It could trim the promotional line 'most widely referenced' but otherwise is appropriately concise and front-loaded with the core purpose.

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

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

For a tool with no parameters, no output schema, and no annotations, the description fully equips the agent with purpose, data coverage, output differentiation (isActual), and typical use cases. Nothing essential is missing for selecting and invoking this tool correctly.

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

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

The tool has zero parameters, so the baseline is 4. The description adds no parameter specifics because there are none. It appropriately focuses on the data content rather than parameter syntax.

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

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

The description clearly states the specific resource (US EIA STEO) and the action (get forecast), listing the exact content areas (crude oil, natural gas, electricity, renewables, petroleum). It distinguishes itself from sibling tools by naming the unique data source and government nature.

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

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

The description implies usage context by naming the target audience (energy traders, logistics companies, macro analysts) but does not explicitly exclude alternative tools or provide comparison. The unique focus on STEO implicitly differentiates it from generic commodity or energy 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently states that observations are 'extracted from news intelligence' and includes the specific data fields returned (direction, magnitude, trade lane, rate values, confidence score, source URL). While it does not explicitly mention read-only status, the verb 'Get' implies it, and the description adds value by explaining the source and contents beyond a simple 'get' operation.

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

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

The description is three sentences, each earning its place: the first states the core function, the second details coverage and content, and the third gives the use case. It is front-loaded with the key verb and resource, and there is no redundant or filler text. This is a model of concise yet informative writing.

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

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

Given the tool has no parameters and no output schema, the description provides all necessary context: what it does, what data it returns, and why it would be used. It covers the indexes, the observation fields, confidence scores, and source URLs, making it complete for an agent to select and invoke the tool correctly. No additional information is needed for a 0-parameter get tool.

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

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

The input schema has zero parameters, so the baseline for this dimension is 4. The description adds no parameter information (correctly, since none exist), but it enriches the tool's semantics by describing the output attributes (direction, magnitude, etc.), which is helpful given the absence of an output schema. This meets the baseline without needing compensation for low schema coverage.

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

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

The description clearly identifies the tool's function as retrieving freight rate index observations from news intelligence, listing the specific indexes covered (BDI, SCFI, WCI, CCFI, HARPEX). This distinguishes it from sibling tools like get_freight_rate_pressure, which focuses on pressure rather than observations. The verb 'get' is specific and the resource is well-defined.

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

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

The description provides clear use context by stating it is 'Used by logistics planners to track rate trends and identify cost pressure signals.' It does not explicitly name alternative tools or say when not to use it, but the use case and content description are sufficient to guide an agent in appropriate scenarios. This aligns with a 'clear context, no exclusions' rating.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly lists what is returned: current values, week-over-week changes, z-score vs 52-week baseline, and trade corridor mapping, plus the full pressure scoring scale. This is comprehensive and leaves no ambiguity about the output.

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 well-structured and front-loaded with the core purpose. Each sentence provides necessary detail: the main output, included metrics, definitions of four indices, and the pressure scale. There is no 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 that there is no output schema, the description fully explains the return values and their meaning. It defines all acronyms and provides the interpretation scale, making the tool's output self-explanatory. For a tool with this complexity, the description is exceptionally complete.

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

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

The input schema is empty, so there are no parameters to describe. The baseline for 0 params is 4, and the description appropriately focuses on output semantics rather than parameters, which adds context without redundancy.

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

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

The description clearly states the tool 'Returns freight rate pressure scores for major shipping and commodity indices (WCI, SCFI, BDI, CRB)', specifying the exact indices and the nature of the output. It differentiates from siblings like get_freight_rate_observations by focusing on pressure scores, not raw data.

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

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

The description implies the tool is used for obtaining pressure scores and defines the indices, but it does not explicitly state when to use this tool versus alternatives such as get_freight_rate_observations or get_freight_transportation_index. No exclusions or alternative recommendations are provided.

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

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

No annotations are provided, so the description carries the burden of disclosure. It explicitly lists the returned data series and adds interpretive value about freight volumes as a leading indicator. It omits response format or access constraints, but for a read-only data retrieval tool, the return content is well specified.

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

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

The description is three sentences long, each serving a distinct purpose: purpose, return components, and context/audience. No redundant phrases or unnecessary details; it is efficient and well-structured.

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

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

Given the absence of an output schema, the description compensates by listing all major return components and providing interpretive context. It does not specify frequency or formatting, but for a no-parameter tool, the description is complete enough to understand the tool's output and value.

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

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

The tool has zero parameters, so parameter semantics are not applicable. With no parameters to document, the baseline score of 4 applies, and the description does not introduce any conflicting parameter information.

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

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

The description opens with a specific verb and resource ('Get the US freight transportation health index from the Bureau of Transportation Statistics') and lists a clear set of output indicators (TSI, truck tonnage, etc.), distinguishing it from sibling tools that focus on rates, rail status, or broader economic indicators.

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

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

The description gives clear context by naming the intended users and use case: 'Used by logistics companies, freight brokers, and economic analysts tracking US freight demand trends.' It does not explicitly exclude alternatives, but the specialized data focus implies when to use this tool.

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

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

With no annotations provided, the description carries the full burden. It transparently describes the return behavior: current score, time-bound comparisons, direction, velocity, pillar-level momentum, and acceleration/deceleration. It discloses the scope (7/14/30-day windows) and the analytical nature (identifies driving pillar). There is no discussion of side effects or permissions, but for a read-only analytics tool this is acceptable. No contradictions with annotations exist.

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

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

The description is four sentences, each earning its place. It front-loads the primary action, then details the return values, then clarifies the use case. There is no redundant information or fluff, making it appropriately sized and well-structured.

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

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

This tool has no parameters, annotations, or output schema, so the description must stand alone. It covers the tool's purpose, the exact data returned (current score, comparisons, direction, velocity, pillar-level momentum), and identifies the driving pillar. It also includes the target audience and use cases. For a simple retrieval tool, this is complete enough.

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

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

The input schema has zero parameters, so the baseline is 4. The description does not add parameter-specific details because none exist. It implicitly indicates the tool requires no inputs by focusing entirely on the output. This is sufficient given the absence of 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?

The description clearly states the tool 'Get trend analysis of the Global Disruption Index over time' with a specific verb and resource. It further differentiates from siblings by detailing unique outputs (7-day, 14-day, 30-day comparisons, velocity, pillar-level momentum) and the specific question it answers. This distinguishes it from other trend tools like get_port_congestion_trends.

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

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

The description provides clear usage context: 'Used by supply chain executives for weekly status briefings and by traders to time entry/exit decisions around supply chain volatility.' It also connects to the specific question 'Is supply chain risk getting better or worse, how fast, and why?' However, it does not explicitly mention alternatives or when not to use this tool, so it lacks explicit 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 are empty, so the description carries the full burden. It discloses generation frequency ('generated every hour from live data'), content structure ('narrative analysis... recommended watch items'), and output suitability ('structured briefs... Slack channels'). It does not detail auth needs or response envelope, but this is a read-only GET-style tool and the description is sufficiently transparent.

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

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

The description is five sentences, each serving a distinct purpose: core function, brief contents, synthetic nature, target audience, and output format. It is front-loaded with the main verb and avoids redundancy, making it efficient and well-structured.

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

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

For a tool with no parameters and no output schema, the description is remarkably complete. It names all five dimensions, explains what each brief contains (current conditions, drivers, risks, watch items), and notes the update frequency. An agent can accurately predict the tool's behavior and return value, though exact response formatting is unspecified.

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

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

The tool has zero parameters, so the schema coverage is vacuous. The description adds no parameter-specific meaning, but it correctly contextualizes the response content. Baseline 4 for zero params is appropriate.

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

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

The description clearly states the tool 'Get AI-generated intelligence briefs for each supply chain dimension', listing the specific dimensions (energy, materials, transportation, macro, manufacturing) and emphasizing narrative synthesis rather than raw data. This distinguishes it from data-focused sibling tools, though it doesn't name 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?

It gives clear usage context: 'Designed for decision-makers who need a quick read' and explicitly contrasts with raw data ('These are not raw data'). It implies when to use this tool over data-monitoring tools, but does not explicitly name alternative tools or state when not to use it.

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

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

With no annotations, the description carries the burden. It discloses the source (news intelligence), event types, and data fields, making the behavior predictable for a read-only getter. It does not mention pagination/freshness, but for a no-parameter call this is adequate.

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

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

Two sentences, front-loaded with action and scope. Every clause adds value—source, coverage, data schema, and use case—without redundancy.

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

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

For a no-parameter tool with no output schema, the description fully specifies the returned event structure (union, employer, location, etc.), covers relevant labor action types, and explains the intended usage context, making it self-contained.

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 are no parameters, so schema coverage is trivially 100%. Baseline for 0 params is 4; the description adds no parameter-specific semantics but none are needed.

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

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

The description clearly states the verb ('Get') and specific resource ('labor actions affecting supply chains'), listing covered event types. It distinguishes itself from siblings by narrowing to labor-related disruptions with concrete fields.

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 provides clear context for use ('assess labor disruption risk at ports and manufacturing facilities') and target users. It does not explicitly mention alternatives or exclusions, but the purpose is unambiguous relative to sibling tools.

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

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

With no annotations, the description fully details the tool's behavior: it monitors 8 power grid regions, detects sudden drops/surges, returns the SMI score with regional breakdown and anomalies from the past 7 days ranked by severity. It also explains the SMI's weather normalization methodology, providing rich behavioral context beyond the tool's name.

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

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

The description is three sentences long, with the core purpose stated first, followed by monitoring details and output, and finally the user context. Every sentence contributes value, and the structure is logical and front-loaded.

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

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

The description covers the return values (current SMI score, regional breakdown, anomalies from past 7 days), the monitored regions, and the methodology. While it does not specify an exact data format, the lack of an output schema is compensated by a clear high-level overview. It could be slightly more precise about output structure or thresholds, but it is adequate for a no-parameter tool.

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

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

The input schema has 0 parameters, so the baseline is 4. The description correctly omits parameter details since there are none to explain. It does not need to add anything beyond the schema.

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

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

The description clearly states the tool's function: detecting unusual electricity demand patterns that signal manufacturing disruptions. It explicitly names the monitored regions and describes the output (SMI score, regional breakdown, anomalies). This differentiates it from sibling tools like get_energy_forecast or get_predictive_signals.

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

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

The description provides clear context for use: it is used by commodity traders for early manufacturing signals and by procurement teams to anticipate supply changes. It implies when to use the tool (when early manufacturing signals or supply change anticipation is needed) but does not explicitly mention when not to use it or name alternative tools.

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

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

With no annotations provided, the description carries the burden of explaining behavior. It discloses the real-time nature, the external data sources, the types of events, and the returned fields (magnitude, severity, coordinates, affected country). This is sufficient for a read-only tool with no parameters.

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

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

The description is two concise sentences. The first sentence states what the tool does and from which sources. The second sentence explains the output and the intended use. Every word adds value; there is no fluff.

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

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

For a no-parameter, no-output-schema, no-annotation tool, the description is complete. It specifies the sources, the data returned (magnitude, severity, coordinates, affected country), and the practical use case. The absence of output schema is compensated by listing the output fields.

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

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

The tool has zero parameters, so the schema is trivially covered. The description does not add parameter-specific detail because none are needed. The baseline score for 0-parameter tools is 4, and no additional constraints are necessary.

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

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

The description clearly states the tool's purpose: retrieving real-time natural disaster alerts from specific sources (USGS, NOAA, GDACS) with a precise threshold (M5.0+). It distinguishes itself from the sibling 'get_disaster_events' by naming the exact sources and the types of events covered.

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

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

The description provides a clear use context: logistics planners and procurement teams rerouting shipments and activating contingency plans. It does not explicitly name alternatives or exclusion criteria, but the use case is specific enough to guide an agent.

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

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

With no annotations, the description carries the full burden. It discloses key behavioral aspects: returns changes relative to historical baselines, identifies accelerating ports, and flags ports approaching critical thresholds. It adds context beyond the tool name by describing output contents. It does not mention data freshness, update frequency, or limitations, but for a read-only analytical tool with no parameters, the description is reasonably transparent.

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

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

The description is three sentences, each earning its place: the first states the core function, the second details what it returns, and the third gives user context. It is front-loaded with the primary purpose and contains no filler. The structure is clear and scannable.

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

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

For a no-parameter tool with no output schema, the description is quite complete. It explains the analytical value, key outputs, and use cases. It could possibly detail the exact format of trends or thresholds, but the description provides sufficient contextual information for an agent to understand its purpose and invocation.

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

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

The tool has zero parameters, so schema coverage is 100% by default. The description contributes no parameter-specific semantics because there are none to explain. Per the rubric, a 0-parameter tool gets a baseline of 4, and the description does not introduce any confusing or unstated 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?

The description clearly identifies the tool as providing port congestion trend analysis, not just current congestion, with a specific verb ('Get') and resource ('port congestion trend analysis'). It distinguishes from siblings by emphasizing 'direction and trajectory' and answering 'Which ports are getting worse and how fast?' The comparison to 'not just current congestion' explicitly differentiates it from likely sibling port_congestion_monitor.

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

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

The description provides clear use cases: 'Used by logistics planners to reroute shipments before congestion peaks, and by importers to anticipate lead time extensions.' This implies when to use the tool (forward-looking trend analysis). However, it does not explicitly name alternatives or state when not to use it, though the 'not just current congestion' phrase hints at alternative current-state 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?

With no annotations, the description carries full burden. It discloses statistical validation (p<=0.01, directional accuracy >=55%), prediction horizon (1 week to 6 months), status categories (ACTIVE, WATCH, CLEAR), and signal count/organization (58 signals, 3 tiers). This is rich operational detail beyond a simple retrieval statement.

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 detailed and well-structured, starting with the core purpose and then providing methodological and usage context. It is somewhat lengthy but each sentence contributes useful information for an agent deciding to invoke it.

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

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

For a zero-parameter tool without an output schema, the description covers the return statuses, prediction targets, and target users. It does not define the exact '3 tiers' or list predictor groups in detail, but overall it is sufficiently complete for invocation.

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

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

The tool has zero parameters, and the schema is empty (coverage 100%). The description adds value by explaining what the returned signal data contains, but no parameter-specific semantics are needed since there are none.

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

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

The description clearly states the tool returns 'Statistically validated leading indicator signals' and specifies what they predict (commodity price movements, manufacturing shifts, macroeconomic changes) and the statuses returned. It distinguishes itself from siblings by emphasizing Granger-causal validation and forward-looking predictive nature.

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 identifies specific use cases and target users: commodity traders for positioning, procurement teams for buy/defer timing, hedge funds for alternative data. It does not explicitly contrast with alternative tools or state when not to use, but the context is clear.

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

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

No annotations are provided, so the description carries the full burden. It discloses data sources and contextual value, but does not disclose behavioral traits such as whether the data is real-time or historical, any rate limits, response format, or whether it is a read-only operation. This is a significant gap.

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

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

The description is informative but slightly long due to the exhaustive metric list. Still, every sentence contributes: the first states purpose, the second provides provenance, and the third gives usage context. It is front-loaded with the core action.

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

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

The description lists many metrics but does not explain the output format, temporal scope (snapshot vs. trend), units, or region granularity. Since there is no output schema, this leaves the agent uncertain about the exact structure of the response. Adequate but with clear gaps.

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

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

The tool has zero parameters, so the baseline is 4. The description adds value by listing the metrics returned and the sources, giving the agent a clear understanding of what data will be provided without needing parameter explanations.

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

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

The description clearly states it retrieves US freight rail performance metrics, enumerating specific data points like average train speed, terminal dwell time, and grain transport rates. This distinguishes it from sibling tools by focusing on rail-specific metrics and naming relevant data sources.

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

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

The description implies usage for monitoring rail-related supply chain bottlenecks ('When rail slows down... this data provides early warning'). However, it does not explicitly compare to sibling tools or state when not to use it, leaving some ambiguity about alternatives like get_port_congestion_trends.

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

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

With no annotations, the description carries the full burden and does so thoroughly. It explicitly enumerates return fields (trigger context, predictor value, direction, narrative paragraph) and describes the narrative content, giving the agent a precise understanding of behavior and output.

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

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

The description is concise (about 80 words) and front-loaded with the primary purpose. Every sentence adds value: purpose, audience, and return details. 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?

For a zero-parameter tool with no output schema, this description is complete. It explains what the tool does, for whom, what each narrative contains, and exactly what is returned. No critical gaps.

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

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

The tool has zero parameters, so there are no parameter details to clarify. The description explains what the tool returns, which is the relevant contextual information for invocation. Baseline of 4 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 uses a specific verb-resource pair ('Get plain-language explanations') and clearly specifies the domain (active predictive signals). It distinguishes itself from sibling tools like get_predictive_signals by explicitly targeting non-quantitative users and contrasting with F-statistics.

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

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

The description provides clear context for when to use this tool: for non-quantitative users wanting the 'why' behind signals, without statistical details. While it does not explicitly name alternative tools, the stated audience and purpose imply when this would be preferred over raw quantitative signal 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?

With no annotations, the description carries full burden. It discloses the report's contents (GDI, disruptions, manufacturing, etc.) and its aggregation behavior, but says nothing about data freshness, whether it triggers on-demand computation, or potential side effects. Since it's a getter with no parameters, this is acceptable but not fully transparent.

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

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

The description is three sentences with the main purpose front-loaded: 'Comprehensive weekly supply chain situation report.' It efficiently enumerates contents and target users. Minor redundancy exists between 'executive-level brief' and 'Used by executives', but overall it is well-structured and waste-free.

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

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

Given there is no output schema and no parameters, the description is the sole documentation. It enumerates six key sections of the report, which is comprehensive for an executive brief. It does not describe the response structure or data sources, but the high-level nature of the tool makes this adequate.

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

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

The tool has 0 parameters, so the baseline is 4. The description adds value by detailing the report's sections (pillar breakdown, risk scores, regional manufacturing, etc.), which helps the agent understand what the returned brief includes, even though no parameters need explanation.

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

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

The description is specific: it produces a 'comprehensive weekly supply chain situation report' combining all data sources. It clearly distinguishes itself from sibling tools like get_gdi_trend_analysis or get_port_congestion_trends by offering a single-call executive summary, making its purpose unambiguous.

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

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

The description explicitly states it 'Designed to answer what happened this week in supply chains?' and is used for 'weekly risk reviews and stakeholder briefings', which clearly implies usage for high-level overviews. While it doesn't explicitly exclude alternative tools, its positioning as a one-stop brief makes the intended context clear.

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

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

With no annotations to lean on, the description discloses important behavioral traits: policies persist 'as long as the policy is in effect', they 'continue to modify GDI risk scores', and each policy returns specific fields (pillar, modifier, effective date, source event). This goes beyond the basic purpose and gives the agent useful expectations about statefulness and output contents.

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

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

The description is three sentences long, front-loaded with the primary action and scope. The second sentence adds a crucial distinction from news alerts, and the third sentence gives practical user context. Every sentence contributes a distinct payload, with no filler or redundancy.

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

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

Given that there is no output schema and no annotations, this description fully compensates. It specifies the types of policies, the persistence behavior, the effect on GDI scores, the fields included per policy, and the intended user base. The tool's simplicity (no parameters) means no further detail is necessary for effective invocation.

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

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

The tool has zero parameters, so the baseline for this dimension is 4. The description does not need to explain parameter syntax; instead, it enriches the context by explaining what the returned policy objects contain, which is more output-focused. This satisfies the baseline without adding parameter-specific details.

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 opens with a specific verb and resource: 'Get active trade policy actions currently impacting supply chain risk', then enumerates concrete policy types (tariffs, sanctions, export controls, import restrictions, regulatory changes). It clearly differentiates from sibling tools by contrasting with news alerts that expire after 72 hours, indicating this is the persistent policy-focused counterpart.

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

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

The description provides clear usage context by naming three user personas (procurement teams, compliance officers, supply chain strategists) and their scenarios. It also implies when to use this over alternative alert tools via the 'Unlike news alerts...' clause. However, it does not explicitly name sibling tool alternatives, so it stops short of a full 5.

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

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

With no annotations, the description carries the full burden. It discloses the return format (article, post, thread), weekly generation cadence, and data verification ('every number traces back to a live data source'). It omits details like auth or rate limits, but for a read-only content retrieval, this is adequate.

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 four sentences, each providing distinct value: what it is, what it returns, data provenance, and intended use. It is appropriately sized and front-loaded, though slightly verbose in listing content details.

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

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

The description fully covers what the tool does and returns, which is essential since there is no output schema. It explains the return structure and data context, making the tool's behavior predictable for an agent.

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

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

The tool has zero parameters, and no parameter descriptions are needed. Per the rubric, 0 params receives a baseline of 4, and the description correctly makes no parameter claims.

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

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

The description clearly identifies the tool as retrieving a specific 'Signal of the Week' content package, listing exact deliverables (Substack article, LinkedIn post, Twitter thread). It distinguishes itself from sibling analytical tools by emphasizing it's a pre-written marketing bundle, not an analysis output.

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 states it's 'Designed for automated content distribution via Claude Desktop + platform MCP servers', providing clear context for when to use. However, it does not explicitly mention alternatives or when not to use, 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?

With no annotations, the description carries the full burden. It discloses the methodology (weather-normalized electricity demand), the inverted scale (lower = stronger), and specific thresholds (0-35 STRONG, etc.). It also reveals the 24-hour lead time. It doesn't mention data freshness or failure modes, but the detail provided is substantial.

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

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

The description is a single paragraph with multiple details, but every sentence adds value: the lead time, the methodology, the regions, the outputs, the scale, and the target audience. It is a bit long, but not bloated, and the core purpose is front-loaded.

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

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

Given the complexity and lack of output schema, the description is quite complete: it tells the agent what the tool does, the data source, the regional breakdown, the scale interpretation, and the intended audience. It could add update frequency or confidence intervals, but for tool selection and invocation, it is sufficient.

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

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

There are zero parameters, so the baseline is 4. The description exceeds this by explaining what the tool returns in detail: regional and national scores, trend direction, and comparison to INDPRO. It defines the scale and interpretation, giving full meaning beyond the empty 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 opens with a specific verb+resource: 'Detect US manufacturing output changes up to 24 hours before official government reports.' It clearly differentiates from sibling tools by naming the patent-pending SMI, the 8 grid regions, and the output (scores, trend, INDPRO comparison). The purpose is immediately unambiguous.

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

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

The description provides clear context for use ('Used by commodity traders, economic analysts, and hedge funds as a leading manufacturing indicator'), implying early insight use case. However, it does not explicitly state when NOT to use it or how it differs from alternatives like get_manufacturing_anomalies, so it stops short of a 5.

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

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

With no annotations, the description carries the full burden. It transparently lists what the tool returns (vessel counts at berth/anchor, congestion score, port status), which is helpful. However, it does not disclose whether this is a snapshot or streaming call, update frequency, or any access-related behaviors. It also doesn't clarify read-only nature, though that may be inferred.

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 organized in four sentences, each with a clear role: purpose, outputs, port coverage, and user applications. It is slightly longer than necessary due to the full port enumeration, but the list is valuable for setting expectations. No filler content is present.

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

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

Given the absence of an output schema and annotations, the description does a solid job of explaining what the tool returns and its scope. It lacks details on data freshness, time periods, or interpretation of the congestion score, but the core functionality and coverage are well covered. This is nearly complete for a no-parameter monitoring tool.

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

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

The tool has zero parameters, so the baseline is 4. The description adds contextual value by enumerating the covered ports, which implicitly tells the user that no input is needed because the scope is fixed. There are no parameter details to explain, so the description appropriately focuses on output and coverage.

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

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

The description clearly states the tool's function: 'Monitor real-time port congestion and vessel traffic at 26 major global ports.' It specifies the exact resources (ports) and outputs (vessel counts, congestion score, port status). It also distinguishes itself from the sibling 'get_port_congestion_trends' by emphasizing 'real-time' and 'historical baseline' comparison.

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

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

The description provides clear usage context by naming target users (freight forwarders, logistics teams, importers) and use cases (monitor delays, plan routing, anticipate lead time changes). It implies real-time monitoring versus historical trends, but does not explicitly state when NOT to use this tool or name alternatives like get_port_congestion_trends.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains the output structure: per-pillar scores, trend direction, and contributing data points. It doesn't mention potential caveats like data freshness or read-only nature, but for a breakdown/reporting tool, the described behavior is sufficiently transparent. Since there are no side effects or complex interactions, this is adequate.

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

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

The description is two sentences long, front-loaded with the primary purpose, followed by specific pillar details and a use case. Every word contributes meaning without redundancy. It is efficient and well-structured.

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

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

Given the tool has no parameters and no output schema, the description is the sole source of information. It fully specifies what the user will receive: scores for each GDI pillar, trend direction, and driving data points, with examples of subcategories. It also clearly states the intended application (diagnosing which risk category is elevated). This is complete for a tool of this simplicity.

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

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

The input schema has zero parameters, so the baseline is 4. The description correctly does not attempt to explain parameters that don't exist. It adds semantic value by clarifying that the tool returns a categorical breakdown, which is inherently parameterless, so there is no ambiguity about inputs.

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

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

The description clearly states the tool's function: 'Get detailed breakdown of supply chain disruption risk by category.' It specifies the exact content: individual scores for each GDI pillar with subcategories, trend, and driving data points. This distinguishes it from sibling tools like 'get_energy_breakdown' or 'get_port_congestion_trends' which focus on singular areas, while this provides a cross-category diagnostic 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?

The description explicitly identifies the target user and scenario: 'Essential for supply chain managers who need to diagnose which risk category is elevated and why.' This provides clear context for when to use the tool. However, it does not name alternative tools or explicitly state when not to use it, but the phrasing implies a diagnostic need rather than a specific single-area deep dive.

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

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

With no annotations, the description carries the full burden. It discloses the real-time nature, the alert categories, the per-alert content (severity, stage, risk score), and the free vs paid tier limitation. This goes beyond minimal expectations, though it does not describe update frequency, response format, or whether alerts are persistent.

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

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

The description is three sentences long, front-loaded with the core purpose, and every sentence adds important context: what comes back, the structure of alerts, and the tier constraint. No waste or redundancy.

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

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

For a zero-parameter tool with no output schema, the description is quite complete: it lists categories, alert contents, and tier limitations. However, it lacks specifics on severity/risk score scales, date ranges, or response size, which for a monitoring tool could be useful for the agent to interpret results. Still, it is largely sufficient.

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

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

The input schema has zero parameters, so the baseline is 4. The description compensates by explaining what the tool returns without needing parameter documentation. It adds value by describing the output structure (severity, stage, risk score) and tier behavior.

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

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

The description clearly states a specific action ('Get real-time supply chain disruption alerts') and resource ('global news intelligence and event detection'). It enumerates specific alert categories (port closures, trade policy changes, etc.), which distinguishes it from sibling tools that focus on singular categories like get_labor_actions or get_natural_disaster_alerts.

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

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

The description provides clear context: this tool returns a broad real-time view of disruption alerts across multiple categories, useful as a high-level monitoring tool. It does not explicitly state when to use this instead of sibling tools, but the scope is evident from the category list, so usage is implied.

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

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

With no annotations provided, the description carries the full burden. It transparently explains the score range (0-100), direction (higher = greater risk), and data inputs (200+ variables, specific sources). This goes beyond the empty schema and gives the agent a solid understanding of expected output and semantics.

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 information-dense but well-structured: it opens with the core purpose, then explains the score and its meaning, lists data sources, and closes with the audience. Every sentence contributes value, with no redundancy or fluff.

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

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

For a zero-input tool with no output schema, the description is comprehensive. It fully defines what the tool returns (GDI score), how to interpret it (higher = more risk), and what data it relies on. It leaves little ambiguity about expected behavior or results.

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

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

The tool has zero parameters, so the baseline is 4. The description correctly focuses on interpreting the output rather than parameter details, which would be irrelevant. No additional parameter info is needed.

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

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

Clearly states it assesses global supply chain disruption risk and returns the Global Disruption Index (GDI), a composite score. This distinguishes it from sibling tools like risk_pillar_breakdown by emphasizing the holistic, real-time nature of the metric.

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

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

Describes the intended users (procurement, logistics, traders, managers) and use case (real-time visibility and risk monitoring). However, it does not explicitly mention alternatives or conditions when this tool should be preferred over related tools, such as risk_pillar_breakdown for detailed pillar analysis.

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