freight-pulse
Server Quality Checklist
Latest release: v1.0.0
- Disambiguation5/5
Each tool targets a highly specific aspect of freight logistics, from spot rates to customs optimization to scenario simulation. The detailed descriptions provide clear boundaries, and even overlapping areas like demurrage are split into distinct tools (appointment_plan vs dnd_strategy) with unique purposes.
Naming Consistency5/5Tool names consistently follow a verb_noun pattern (e.g., get_spot_rate, create_watch, check_watches) or are descriptive noun phrases (e.g., market_report, ship_decision). All use lowercase with underscores, with no mixing of conventions or irregular patterns.
Tool Count4/5At 47 tools, the count is high, reflecting the server's exhaustive coverage of freight logistics (rates, costs, compliance, risk, optimization). While above the typical sweet spot, the breadth justifies the number, and each tool serves a distinct function without redundancy.
Completeness5/5The tool surface covers virtually the entire lifecycle of freight decision-making: market intelligence, cost analysis, regulatory compliance, risk management, procurement, and optimization. Minor gaps (e.g., no tool for real-time tracking) are outside the server's decision-support scope, making it remarkably complete for its stated purpose.
Average 4.5/5 across 47 of 47 tools scored. Lowest: 3.7/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 1 commit in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
This repository includes a glama.json configuration file.
If you are the author, simply .
If the server belongs to an organization, first add
glama.jsonto the root of your repository:{ "$schema": "https://glama.ai/mcp/schemas/server.json", "maintainers": [ "your-github-username" ] }Then . Browse examples.
Add related servers to improve discoverability.
How to sync the server with GitHub?
Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.
To manually sync the server, click the "Sync Server" button in the MCP server admin interface.
How is the quality score calculated?
The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).
Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.
Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).
Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.
Tool Scores
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It thoroughly discloses the tool's behavior: returns indicative breakdown, HS classification, duty rules per destination/origin, de minimis thresholds, VAT computation, and caveats. This is comprehensive and sets accurate expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long and detailed, packing a lot of information. While it is well-structured with clear sections, it could be more concise. Every sentence earns its place, but brevity could improve agent parsing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 12 parameters, no output schema, and no annotations, the description is remarkably complete. It covers all major aspects: output breakdown, classification, duty rules, VAT, de minimis, caveats, and even payment. It meets the needs for a complex estimation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, but the tool description adds valuable context beyond field definitions, e.g., explaining that origin_port drives trade remedies and FTA logic. This helps the agent understand parameter significance in the broader computation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns a landed cost breakdown with HS classification and duty modeling. It covers a specific domain (imports) and many related concepts, but does not explicitly differentiate from siblings like total_cost_ownership or get_all_in_rate, leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains what the tool returns and the components involved, implying it is for estimating landed costs. However, it lacks explicit guidance on when to use this versus alternatives (e.g., get_spot_rate for freight only) and does not mention exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes the internal process but does not explicitly disclose whether the tool is read-only, destructive, or requires authentication. The honesty note and pricing info are present but do not replace behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is informative and front-loaded with the main purpose. Each sentence adds value, though the pricing note could be considered extraneous. Overall structure is clear and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and only one optional parameter, the description thoroughly explains the return value (alerts with observed value, reason, severity) and the internal process. It also includes a caveat about model reliability, making it complete for an agent to use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers both parameters with 100% description coverage. The description repeats the schema's info about watch_id without adding new meaning, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool evaluates lane watches against live modeled market and returns alerts that fired. It specifies the resource (watches) and action (check), and distinguishes from sibling tools like create_watch.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool: to check one watch by passing watch_id or all watches by omitting it. It also implies it's a daily poll. It does not explicitly state when not to use or alternatives, but usage is clear for a single-purpose tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description fully covers behavioral traits. It honestly discloses that the tool uses a model, not live terminal feeds (eModal/Voyage/TideWorks), is indicative, and mentions premium pricing (pay per call with USDC). This level of transparency is exemplary.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is detailed and well-structured, front-loading the core purpose and process. While every sentence adds value, it is somewhat lengthy (including examples and pricing). A slightly more concise version would earn a 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, no output schema), the description is complete: it explains inputs, the modeling approach, outputs (optimal pickup window, sequence, D&D savings), caveats, and pricing. No gaps remain for an agent to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so each parameter is already described. The tool description adds overall context but does not significantly enhance parameter meanings beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: planning terminal appointments and box sequence to avoid demurrage & detention. It explains the inputs and outputs in detail. However, it does not explicitly distinguish from sibling tools like dnd_strategy, which may overlap, so it misses the highest marks for differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage contexts (congested vs. fluid ports) and sets expectations that it is indicative, not a live feed. However, it does not provide explicit guidance on when to use this tool versus alternatives (e.g., dnd_strategy) or 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.
- Behavior4/5
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 that results are MODELED, indicative, and not a guarantee; mentions pricing (pay per call with x402); and explains the output structure (plays ranked by urgency). This is transparent about limitations and behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but concise for the amount of information it conveys. It starts with a clear use case, lists actions, pricing, and limitations. It could be slightly more structured, but every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description compensates by explaining the return: playbook with cost and time deltas, ranking by urgency. It also advises to validate with carrier/forwarder. This is complete enough for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with descriptions for each parameter. The description adds useful context like the effect of 'disruption_type' (force a specific what-if) and 'urgency' parameter, but these are already mentioned in the schema. Baseline 3 applies as the schema is already thorough.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: given a lane, it detects active disruptions and generates an actionable playbook with routing, modal shift, port swap, pre-positioning, and re-prioritization options. It distinguishes itself from sibling tools like 'simulate_scenario' or 'booking_strategy' by focusing on disruption contingency.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use it ('My route just broke — what do I do AHEAD of the next sailing?') and lists required and optional parameters. It doesn't explicitly state when not to use it or provide alternatives, but the context of sibling tools implies it's for immediate disruption response.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the tool is modeled and indicative, not a live feed or insurance-grade, and mentions pay-per-call pricing. However, it does not detail data freshness or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long and dense with all-caps emphasis, but front-loads the core concept. While informative, it could be more structured and concise; several sentences explain individual risk dimensions in detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, no output schema), the description is highly complete: it explains what the score represents, lists all risk factors, describes output (score, breakdown, mitigations), and includes limitations and pricing. It covers what an agent needs to know.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and each parameter has a clear description in the schema. The tool description adds context, e.g., transit_country overlays geopolitical risk, carrier_count impacts concentration, adding meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool computes a lane-risk score (0-100) for supply-chain risk mapping. It specifies the verb 'compose' and lists multiple risk dimensions, distinguishing it from sibling tools like carbon_footprint or get_lane_trend.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for risk mapping by a supply-chain director but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusion criteria. No guidance on when not to use is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It transparently explains return values (market-rate bands, model limitations with 'Honest (regla 7)'), the process timeline, and pricing model. It does not cover auth needs or rate limits but sufficiently discloses behavioral traits for a read-like build operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is verbose yet well-structured, front-loading the core purpose and then detailing outputs. Every sentence adds value, justifying the length. Minor reduction for not being as tight as possible.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and two straightforward parameters, the description fully explains return values (per-lane details, criteria, bid sheet, timeline, total spend) and even links to evaluate_bids. It is complete for an agent to understand tool usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds meaningful context: lanes are explained as 'your lanes with annual volumes' and priority as 'cost, reliability, balanced'. It also hints at optional container_type, enhancing schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with a clear verb+resource: 'Build the structure of a freight RFP / TENDER to put your ocean network out to bid.' It distinctly defines the tool's purpose and differentiates it from siblings like evaluate_bids, which scores answers rather than constructing the framework.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied: provide lanes and volumes to get a tender structure. The description mentions pairing with evaluate_bids but lacks explicit when-to-use vs alternatives or when-not-to-use guidance. Sibling context shows many related tools, but no comparative advice is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It honestly discloses that abatement costs are modeled and indicative, that offsets are flagged as compensation not reduction, and that targets beyond reduction levers are labeled. It also mentions pricing model (PREMIUM: pay per call). No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively long but well-structured, starting with the main purpose then detailing levers and outputs. While each sentence adds value, it could be slightly more concise; however, it remains clear and informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and lack of output schema, the description covers inputs, levers, return values (ordered roadmap with tonnes abated, cost, etc.), limitations, and pricing. It is thorough and leaves minimal gaps for an agent to understand usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds meaning beyond the schema by explaining the role of parameters (e.g., origin_port/dest_port for lane-based baseline, baseline_co2e_tonnes for network footprint, allowed_levers for restriction, cost_band for sensitivity). It provides context that the schema alone does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to create a decarbonization roadmap for a transport network. It uses specific verbs like 'cut the carbon' and 'walks the abatement levers', and lists the exact levers involved. It distinguishes from sibling tools like carbon_footprint (which only measures) and optimize_network (which is broader).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit conditions for use: 'Give a lane (or an annual network footprint in tonnes CO2e) and a reduction TARGET %'. It explains what the tool does with the inputs. However, it does not explicitly state when not to use this tool or mention alternatives, though the context implies it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: scoring on cost, reliability, and coverage; detecting and penalizing low-balls; selecting credible awards; and providing network-level cost comparisons. It also clarifies it is a modeled decision aid, not a procurement decision.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy and includes extraneous details like 'Honest (regla 7)' and payment information, which add clutter. It front-loads the main purpose but could be trimmed for better conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains the output (best credible award per lane, network cost comparison, low-ball flags) and addresses the tool's limitations. It is sufficiently complete for a tool with two parameters, though a note on pagination or result format could enhance completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage with property descriptions for 'lanes' and 'priority'. The description adds operational context (e.g., annual volumes, carrier bids) but does not significantly augment the schema's parameter meaning beyond what is already described.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool evaluates carrier bids on a freight tender to pick the best award per lane. It provides specific details on inputs (lanes with bids) and outputs (scored awards, network cost comparison, low-ball flags), effectively distinguishing it from sibling tools like 'select_provider' or 'carrier_recommendation'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates when to use the tool (when evaluating bids on a tender) and notes it is a decision aid, not a procurement decision. It advises verifying rates contractually but does not explicitly state when not to use it or mention alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description covers behavioral traits: it uses a modeled dispersion around an index mid, not real quotes, and explains the pricing model (pay per call or prepaid key). It also describes the return values (percentile, over/under pay, corrective lever). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is verbose and includes marketing language ('am I being clamped?', 'Proves:'). While it front-loads purpose and includes critical details, it could be more concise. Every sentence adds value, but the length reduces scanability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains return values (percentile, over/under pay, savings, lever). With 8 parameters and no annotations, it covers use cases, limitations, and pricing. It is sufficiently complete for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining parameter intent (paid_rate_usd as 'the rate you currently PAY'), usage context (annual_containers to annualize savings), and how optional parameters affect benchmarking (is_contract flags high contracts). This goes beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool benchmarks a rate against market bands, using specific verbs like 'Benchmark' and explaining the output (percentile, over/under payment). It distinguishes itself from sibling tools like 'get_spot_rate' or 'market_report' by focusing on comparing an existing rate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use: 'the am I being clamped? check every shipper wants.' It provides guidance on required inputs (lane + paid_rate_usd) and mentions honest limitations (modeled dispersion, not real quotes), though it lacks explicit when-not-to-use scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses that the tool composes outputs from other engines, is not audited, and requires premium payment. It mentions 'regla 7' as a transparency rule. While it does not explicitly state read-only behavior, the nature of a calculation tool implies no side effects. The description is fairly transparent about limitations and cost.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is verbose with multiple paragraphs, including extensive examples and disclaimers. While the front-loading is present ('ONE comparable number per strategy'), the level of detail, such as the specific components and ranking dynamics, could be trimmed without losing essential guidance. The inclusion of payment details also adds length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (17 parameters, no output schema), the description is quite complete. It explains the logic, the components, and the expected output (ranking with TCO breakdown). It does not explicitly describe the return format or schema, but the description implies a ranked list of strategies with score breakdown. The large number of sibling tools also increases the need for clarity, which the description partially addresses.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are well-documented. The description adds value by explaining the role of key parameters like fob_value (baseline for scaling), candidates (default China+1), and the various optional cost factors (holding rate, capital rate, risk cost factor) in the overall TCO calculation. This context goes beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: computing total cost of ownership per strategy, ranking strategies, and explaining ranking dynamics. It uses specific verb phrases like 'composes PER STRATEGY' and 'ranks the strategies by TOTAL TCO'. It distinguishes itself as the comprehensive tool that 'ties the entire freight-pulse stack into one decision', clearly differentiating it from sibling tools like get_landed_cost or lane_risk_index.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly targets CFO and supply-chain-director roles and provides concrete use cases (nearshore vs China, air for high-value goods). It also includes an honest disclaimer about the indicative nature of the outputs. However, it does not explicitly state when NOT to use this tool or point to specific alternative sibling tools for more granular analyses.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for disclosing behavioral traits. It clearly states the tool is 'INDICATIVE, NOT a live waiting-time feed' and 'MODELED structural typical + a dated disruption overlay.' It also mentions premium pricing and conversion details. This level of transparency is commendable, though it could mention if the tool 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.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is verbose and dense, covering extensive detail in a single paragraph. While it front-loads the main purpose, it could benefit from bullet points or structured sections for readability. However, every sentence adds value, so it is not overly wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and lack of output schema, the description provides comprehensive information about return values (congestion index, waiting days, operational-risk score, active disruptions) and data sources. It also clarifies limitations and pricing, ensuring the agent has enough context to invoke the tool appropriately.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
100% schema coverage lowers the burden. The description provides additional context for the `ship_date` parameter, explaining how disruptions are evaluated relative to the date. For other parameters, it references the schema's descriptions (e.g., same normalization as get_spot_rate). This adds meaning beyond the schema for at least one parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to provide port congestion and disruption intelligence for a lane. It explicitly distinguishes itself from rate tools, indicating its unique role in assessing operational port status, not costs. This specificity helps the agent understand exactly what this tool offers versus siblings like get_spot_rate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description contrasts the tool with rate tools, guiding when to use it ('this tells you whether the PORTS can actually clear it on schedule'). It also mentions pricing details. However, it does not explicitly list alternative tools or scenarios to avoid using it, which would further enhance guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description implies read-only via 'Read', discloses cost details, and mentions that data is based on own empirical logs with small samples flagged, adding transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description contains multiple sentences with some marketing language and could be more concise, though it front-loads the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Comprehensively describes the return fields (on-time %, delay, rates, reliability score, trend, ranking, best/worst performer), no output schema exists, and includes data source and cost context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds value beyond the schema by explaining how to use the 'subject' parameter (omit for whole network, pass one to drill in) and mentions disambiguation via 'subject_type'. Schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads a scorecard of KPIs for suppliers, carriers, or lanes, distinguishing it from other analytics tools by specifying it's based on data from record_performance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides guidance on using the optional 'subject' parameter to drill down into a specific entity or omit for the whole network, but does not explicitly mention alternatives or when not to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It explains that the checklist is indicative, not binding, and details how goods and destination trigger specific documents. It also mentions payment premium and normalization. No contradictions or missing side effects are apparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured, starting with the main purpose and then detailing components. It is efficiently packed with information, though it includes some marketing language ('PREMIUM: pay per call') that is less essential. Overall, it is concise given the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (6 parameters, no output schema), the description is quite complete. It explains what the checklist contains, how optional inputs affect it, and what limitations exist. The return format is implied but not detailed, which is acceptable for a checklist tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents each parameter. The description adds substantial value by explaining how each parameter influences the checklist (e.g., product triggers goods-specific docs, incoterm tags responsibilities). This goes beyond schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool produces a checklist of trade documents required for shipping goods to a destination. It specifies the commercial set, goods-triggered specials, destination filings, and certificate of origin, which is distinct from sibling tools like 'check_lc_documents' or 'export_compliance'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit when-to-use guidance: when you need to know required documents for a shipment. It lists necessary inputs (origin, destination, product/hs_code) and optional parameters, and clarifies that without product/hs_code, you still get core and destination sets. It also warns that this is not a binding filing list. However, it does not explicitly state when not to use 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.
- Behavior4/5
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 clearly discloses behavior: scoring archetypes, ranking, recommending type+pairing, and emitting a scorecard. It also includes honesty disclaimers about the indicative nature and premium payment.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections: purpose, usage, examples, honesty note, premium. It front-loads key information, though slightly verbose; each sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 7 parameters (none required) and no output schema, the description covers the decision logic, input effects, and output deliverables (scorecard). It lacks detail on exact output format but is otherwise complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% parameter description coverage, so baseline is 3. The description adds significant value by explaining how parameters like specialisation and volume affect the ranking, providing context beyond the schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly defines the tool's purpose: selecting and grading freight intermediaries. It uses specific verbs ('choose', 'grade') and resource ('freight INTERMEDIARY'), and distinguishes from sibling tools like carrier_recommendation by focusing on intermediary archetypes rather than specific carriers.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool: when you need to choose an intermediary type based on a needs profile. It provides explicit context through examples (e.g., reefer-heavy need leads to a niche forwarder), but does not explicitly 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.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully bears the transparency burden. It discloses that the tool provides modeled estimates (not live), details the calculations (volatility, 95% adverse move, hedge ratio using media-variance), and states it does not give financial advice. It also mentions premium cost.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured: purpose first, then explanation, outputs, caveats, and cost. It is front-loaded and informative, though somewhat verbose with phrases like 'Honest (regla 7)' that could be trimmed without losing value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity, no output schema, and no annotations, the description is thorough. It explains all return values (exposure in local currency, volatility, 95% move, hedge ratio, forward points, laddered plan) and limitations, leaving no major gaps for an agent to understand its behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description restates the purpose of parameters like local_currency and annual_freight_spend_usd but does not add significant new information beyond what the schema descriptions already provide.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Quantify and hedge the CURRENCY RISK of your ocean-freight spend.' It specifies inputs and outputs, and distinguishes itself from other tools by focusing on ocean-freight FX exposure, not live quotes or financial advice.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use: for non-US shippers with USD freight bills. It includes a caveat that it is a modeled reference analysis, not live quotes or advice, and advises consulting a professional. However, it lacks explicit comparison to sibling tools or a 'when not to use' section.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the report is indicative decision support (not a quote/booking/legal advice), names which engines contributed, and states availability issues honestly. It also explicitly mentions premium pricing (pay per call).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured with numbered sections and front-loaded purpose. Some redundancy exists (e.g., listing all sections in detail), but it remains efficient for a complex tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description fully explains the return value by enumerating the report sections. It also covers how optional parameters affect output, pricing, and limitations, making it complete for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds some context (e.g., product/value unlock sections, defaults for container_type and ship_date) but does not significantly expand on the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool composes a comprehensive executive market intelligence report for a freight lane, listing six detailed sections plus an executive summary, headline, and action list. It distinguishes itself from siblings (e.g., get_spot_rate, carrier_recommendation) by being an aggregate report, not a single data point.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when a committee-ready brief is needed and mentions optional parameters to deepen the report. It does not explicitly state when not to use it or name alternatives, but the context of sibling tools makes the distinction clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: it is indicative (not a stow guarantee), capped by weight/height, and details limitations like crush strength, interlocking, and overhang. It also mentions premium pricing (pay per call). This is highly transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but not overly verbose; it front-loads the main purpose and then efficiently covers inputs, outputs, comparisons, limitations, and pricing. Every sentence adds value, though slightly long for a tool description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with 9 optional parameters and no output schema, the description covers purpose, all input semantics, output computation, trade-offs, limitations, and pricing. It is self-contained and fully contextual.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all parameters. The description adds context on how inputs are used (e.g., 'best layer pattern from both case orientations + pinwheel × layers'), but does not significantly extend the schema's own parameter descriptions. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool optimizes palletization across the full chain, computes cases per pallet, pallets per container, cube utilization, and contrasts with floor-loaded. It distinguishes itself from a 'box→container load optimizer', likely a sibling tool, making its unique purpose very clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies required inputs (case size, pallet standard, container) and outputs, indicating when to use the tool. It contrasts with floor-loaded and mentions the trade-off, but does not explicitly list alternative tool names or state when not to use it. Still, it provides solid guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It details that the tool integrates multiple engines, returns recommendations, and is non-binding. It mentions premium payment but does not disclose error conditions or side effects, though for a decision support tool this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is verbose and uses marketing language ('makes freight-pulse insustituible') and Spanish terms ('PUESTO EN DESTINO'), which reduces clarity for an English-only agent. Despite front-loading the purpose, it could be more concise and structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 14 parameters, no output schema, and no annotations, the description fully explains what the tool returns (mode, carrier, timing, cost, risks) and how it works, including payment details. It is comprehensive for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds significant context for parameters (e.g., 'value drives mode-choice', 'urgency shifts recommendation', 'deadline adds stockout cost'), going well beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is the UNIFIED decision tool that integrates every freight-pulse layer into one actionable answer for a concrete shipment. It specifies output components and distinguishes from sibling tools that focus on individual layers.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains input requirements and output, and notes it is 'indicative decision support — not a booking or a quote', providing context. However, it lacks explicit guidance on when to use this holistic tool versus individual layer tools from the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that figures are modeled indicative bands, not quotes or tariffs, explains the alliance realignment and how priority affects ranking, and notes that results refine lane OTP for the top pick. All behavioral traits are transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-organized, front-loaded with purpose. Each sentence adds value, covering nuances of alliance models and priority logic. Could be more concise, but the detail is justified by complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters, no output schema, the description explains parameter semantics, result computation, and limitations. It lacks explicit return format but is otherwise thorough for a complex tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds meaning: explains port normalization, priority synonyms, container_type as informational, and ship_date's role. It goes beyond the schema to clarify usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool recommends which carrier or alliance to sail with on a lane, positioning it as a decision aid after booking time and mode. It distinguishes from siblings by focusing on carrier selection rather than rates or routes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
It explains when to use (third decision in booking process) and how priority flips ranking, but does not explicitly state when not to use or list alternative tools. Context is clear but exclusions are absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It discloses that the tool reads congestion data, builds dwell distributions, and computes probabilistic costs. It does not mention side effects (likely read-only). The methodology is transparent, including modeled assumptions and payment methods.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is comprehensive but well-structured. It starts with the main purpose, explains methodology, then lists parameters with their roles. It includes necessary caveats and payment info without being verbose. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description thoroughly explains the return values: dwell distribution, probability of breach, expected chargeable days, expected D&D cost, p90 cost, and a recommended free-day target. It covers inputs and outputs completely for this complex tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by explaining how each parameter influences the analysis (e.g., dest_port drives congestion, ship_date sets evaluation date, carrier refines free days). It enriches understanding of parameter relationships.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it optimizes demurrage & detention free-time strategy for a destination, using specific verbs like 'optimize' and reference to 'beyond the simple D&D line'. It distinguishes itself from sibling tools like 'booking_strategy' or 'carrier_recommendation' by focusing on free-day negotiation and expected cost modeling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use (to negotiate free days, evaluate expected D&D costs) and provides context on destination congestion and dwell distribution. It mentions options like passing a carrier or mean dwell. It lacks explicit negative usage guidance but includes a caveat that it's not a carrier's filed tariff.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: it is a recommendation tool using market-typical bands (not a broker's quote), details premium calculation components, payment per call or prepaid key, and UN/LOCODE normalization. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and front-loaded with the main purpose, then breaks down clauses, premium calculation, Incoterms, and payment. It is somewhat long but each sentence adds value; could be slightly more concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (10 parameters, no output schema), the description is thorough, covering purpose, premium components, clauses, Incoterms, and payment. It lacks explicit output format but the premium computation details imply what is returned.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds extra context beyond schema descriptions, such as how origin port affects war-risk premium and how product classifies loss profile. This adds value without being redundant.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool recommends cost-effective marine cargo insurance, specifying the verb 'Recommend' and the resource 'marine cargo insurance'. It distinguishes from siblings by detailing the comparison of Institute Cargo Clauses, which is unique among the listed tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use, including Incoterms implications (CIF, CIP, FOB/CFR/CPT) and payment model. It does not explicitly list alternatives among siblings, but the detailed Incoterms guidance helps decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully bears the burden. It discloses the core formula (safety stock = z·σ_LTD, reorder point, Wilson EOQ), indicates it uses textbook OR models, and mentions 'premium pay per call.' It is transparent about the computational behavior and cost model.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single coherent paragraph that front-loads the primary purpose. At roughly 10 sentences, it is fairly concise for the complexity of the tool, though it could be slightly restructured for easier scanning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and lack of output schema, the description adequately explains the return values (safety stock, reorder point, EOQ, total cost per mode) and the underlying trade-off logic. It covers the key parameters and behavior, though it omits potential error conditions or edge cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining how parameters like annual_demand_units and unit_value_usd drive the inventory policy and trade-off, and it contextualizes optional params like service level and holding rate within the formula. This exceeds mere repetition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Size the INVENTORY a freight decision forces you to hold.' It specifies the resource (inventory) and action (size) and distinguishes from siblings like total_cost_ownership by focusing on safety stock and reorder point calculations driven by freight mode choices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells the user to 'Give the lane + your annual demand (units) + unit value' and explains the trade-off between ocean baseline and air option. While it provides clear context for use, it does not explicitly exclude alternatives or mention when not to use this tool relative to siblings like compare_modes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Describes global optimization process, network constraints (budget, service, CO2), outputs (top saving lanes, consolidation, trade-offs), and indicative nature. Also discloses premium cost. Very transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
Dense paragraph but front-loads purpose and contrast with single-lane tools. Every sentence adds value. Could use bullet points for constraints, but overall efficient for the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers what the tool does, how it works, constraints, and outputs (top saving lanes, consolidation, trade-offs). Missing explicit output format, but no output schema exists; description gives adequate high-level picture for a complex tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage 100%, baseline 3. Description adds context: explains lanes as a portfolio, budget shifts lanes to contracts, min_reliability prevents cutting service, max_co2 targets carbon lanes, consolidation_threshold triggers tier. Adds significant meaning beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it optimizes an entire annual lane portfolio, contrasting with single-lane tools. Uses specific verb+resource: 'Optimize a shipper's ENTIRE annual lane PORTFOLIO at once'. Distinguishes from siblings like get_lane_trend, get_spot_rate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explains this tool is for portfolio-level optimization, not single lanes. Mentions it reuses same engines for coherence. Implicitly suggests when to use (when you have a set of lanes with volumes), but lacks explicit when-not-to-use or alternative tool names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavioral traits: it models three strategies, builds a spot distribution, reads market regime, computes break-even, optimizes mix, models MQC penalties, and quantifies value of protection. It also mentions pricing and UN/LOCODE normalization. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but efficient given the tool's complexity. It front-loads the core purpose in the first sentence, then provides necessary behavioral details. While dense, every sentence adds unique information; however, it could be slightly more structured with paragraphs for readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description thoroughly explains the internal logic but lacks information about the return value or output format (no output schema provided). It does not specify whether the output is a recommendation, a comparison table, or a percentage split. This gap reduces completeness for execution.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, but the description adds significant meaning beyond the schema: it explains the role of annual_volume as the basis of trade-off, risk_tolerance setting the mean-variance λ, volume_cv driving shortfall risk, and contract_rate_offered being scored against break-even. This enriches the agent's understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool decides 'OCEAN SOURCING STRATEGY' for a lane over a year—locking contract, staying on spot, or splitting. It distinguishes from siblings by specifying this is the 'procurement/CFO decision' and not a tactical booking tool like 'book this box now'. The verb 'decide' and resource 'sourcing strategy' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context: 'This is the procurement/CFO decision the other tools don't touch'. It implies usage when strategic sourcing over a year is needed, contrasting with tactical tools. However, it does not explicitly list alternative tools or conditions for when not to use it, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the burden. It discloses that the tool never silently adjusts, reports baseline/scenario/deltas, and requires payment via x402 or prepaid key. It also mentions port normalization and the structural adjustments are transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-structured, front-loading the main purpose and scenarios. It could be slightly more concise (e.g., 'regla 7' might be obscure to some agents), but overall it efficiently uses space.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 8 parameters and no output schema, the description adequately explains inputs and their effects. It mentions deltas and baseline but does not detail the exact output structure (e.g., format of returned data). Slightly more detail on return values would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds significant value by explaining scenarios and their effects (e.g., 'fuel-spike: bunker VLSFO up X% → BAF/bunker portion rises') and details the purpose of parameters like fuel_spike_pct, tariff_delta_pp, and value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool runs a 'what-if' on a lane, recomputing COST and TIME impact of structural changes. It lists specific scenarios (red-sea-reopen, fuel-spike, cny, tariff-change) and distinguishes itself from siblings by focusing on counterfactual simulations, not predictions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit scenarios and when to use each (e.g., 'only material on Suez-exposed lanes', 'material on China-origin lanes'). It also clarifies it is a modeled counterfactual, not a prediction. However, it does not explicitly mention when NOT to use this tool or list alternatives among the 48 sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that figures are modeled planning data, not certified, and mentions the premium payment model (x402 USDC or prepaid key). However, it does not explicitly state whether the tool is read-only or any authentication/rate limit details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured with clear sections for each cargo type. Every sentence adds value, though some redundancy exists. The length is justified by the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 13 parameters, no output schema, and no annotations, the description thoroughly covers both input usage and output expectations for all three cargo types, including the premium model and data disclaimer. It is complete for an assessment tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant context beyond schema descriptions: it explains how parameters interact (e.g., product inferring DG class), details output for each cargo type, and clarifies optionality. This exceeds the baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly defines the tool's purpose: assessing special/non-standard cargo (dangerous goods, reefer, out-of-gauge) for a lane, distinguishing it from standard dry box rate models and sibling tools like get_spot_rate. The verb 'assess' is specific and the resource ('SPECIAL / NON-STANDARD CARGO') 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.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (for cargo that a plain dry box model can't price) and what it returns for each cargo type. It implies not to use for standard cargo (use get_spot_rate) but does not explicitly name all alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description thoroughly discloses behavioral traits: it reads demand pressure from seasonality and equipment calendars, returns indicative recommendations (not guarantees), and mentions payment method (USDC or prepaid key). Without annotations, this fully informs the agent of the tool's read-only, analytical nature and its limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is comprehensive and well-structured, starting with the core purpose and then detailing the inputs, outputs, and behavioral caveats. While not extremely concise, the length is justified by the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description provides a complete picture: inputs, internal logic, output structure (booking window, rollover probabilities, trade-off), and behavioral caveats. Without an output schema, this fully equips the agent to understand what the tool returns and how to use the results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although the input schema already describes all parameters (100% coverage), the description adds value by explaining how parameters like criticality and annual_containers influence the recommendation (e.g., criticality buffer, named-account trigger). This goes beyond the schema's basic descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to advise on booking strategy for space reservation, including recommendations for spot vs guaranteed vs named-account. It distinguishes from sibling tools like get_spot_rate (which likely just provides rates) and carrier_recommendation by focusing on the strategic booking decision with criticality and volume inputs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use the tool (for space reservation decisions given lane, ship date, criticality) and what inputs are needed. However, it does not explicitly state when not to use or compare to sibling tools like get_spot_rate or carrier_recommendation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It details the rule-based checking process, lists specific discrepancy checks, warns against treating it as a bank determination or legal advice, and mentions it returns severity mix and what couldn't be checked.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but front-loaded with a compelling question and key statistics. Every sentence adds relevant detail about capabilities, limitations, and pricing. Minor redundancy could be trimmed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 25 parameters, no output schema, and no annotations, the description fully explains input requirements, the process, and output (discrepancies with UCP articles/remedies, clean/rejected status, severity mix). It even provides a legal disclaimer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all 25 parameters. The description adds value by explaining how parameters are used in specific checks (e.g., invoice amount over credit, currency mismatch), tying them to UCP articles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it checks letter-of-credit documents under UCP 600 for discrepancies, listing specific rules checked and outputting discrepancies with remedies. It uniquely identifies this tool among siblings as specialized for LC document checking.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for pre-checking LC presentations before submission to a bank, mentioning premium pricing. It does not explicitly state when not to use or provide alternatives, but the specialized domain makes usage clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It is highly transparent: explains the survival model, expected total cost calculations, assumptions, and includes a disclaimer about the indicative nature. Even mentions payment method.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured: purpose first, then details, then disclaimer. It is packed with information but could be slightly more concise. Front-loads key purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 11 parameters, no output schema, and no annotations, the description is very complete. It explains the model, economics, inputs, outputs, and limitations. No obvious gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all 11 parameters. The description adds value by explaining how parameters like cargo_value and product are used in economic analysis, beyond basic schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides cold-chain/pharma compliance for temperature-controlled shipments, returning specific outputs like temperature requirement, excursion risk, recommended mode and packaging. It is distinct from sibling tools which cover other logistics functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use: for temperature-controlled shipments beyond a reefer setpoint, and gives examples of products and sensitivity. It does not explicitly state when not to use, but the context implies it is specialized for cold chain.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavioral traits: it states that figures are modeled and indicative, not legal advice, and requires confirmation with a licensed broker. It also notes specific limitations like Section 301 ineligibility for drawback and that the engine reuses the landed-cost calculation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but well-structured and front-loaded with the purpose. Every sentence adds value, providing detailed information about the levers, outputs, and caveats. However, some redundancy could be trimmed for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 parameters, no output schema), the description is fully complete. It explains inputs, outputs (ranked levers with savings and catch), the underlying engine, and important disclaimers, leaving no major gaps for the agent to infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with descriptions for all 7 parameters. The description adds significant value by explaining the meaning of each parameter (e.g., flow examples, required fields) and providing context beyond the schema, such as the trade flow options and the requirement for FOB value as duty base.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: finding duty-saving levers for importers. It specifies the exact inputs (product/HS code, lane, FOB value, trade flow) and outputs (ranked savings with details). It distinguishes from sibling tools like 'customs_valuation' and 'get_landed_cost' by focusing on optimization strategies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit instructions on what to provide (product or HS code, lane, FOB value, trade flow) and what the tool returns. It mentions the context of use (importer seeking duty savings) but does not explicitly state when not to use or compare with alternatives, though it is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Describes server-side processing with accumulated history and freight-seasonality model. Details statistical method (Holt-Winters/ETS), output components including backtest metrics, and states 'Indicative market intelligence, not a carrier quote.' Clearly discloses premium nature and prerequisite call to get_spot_rate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but front-loads the main purpose. Every sentence earns its place by adding value. Could be slightly trimmed, but given the tool's complexity and lack of output schema, the detail is justified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite 5 parameters and no output schema, the description thoroughly explains all outputs, methodology, limitations, and prerequisites. Covers what the tool returns, how it works, and how to use it effectively, making the agent fully informed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline 3. The description adds meaningful context: explains weeks cap on history, ship_date used for seasonality calendar, forecast_weeks with widening intervals. This aids understanding beyond schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool forecasts ocean spot rates for a lane and provides a grounded recommendation. It lists specific outputs: time series, statistical forecast, seasonality calendar, anomaly detection, and a concrete book-now/wait call. It distinguishes from siblings by noting port normalization same as get_spot_rate and suggesting calling get_spot_rate first.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit usage guidance: 'Tip: call get_spot_rate (free) on a lane first — it seeds the history.' Also mentions premium payment and unlock instructions. Does not explicitly state when not to use or contrast with siblings, but the context of sibling tools (many different purposes) makes this acceptable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must cover behavioral traits. It explains cross-validation of indices, port normalization, container defaults, and return fields (confidence score, market direction). Lacks detail on error cases but is overall transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose and covers many details in a structured way. Each sentence adds value, though it could be slightly shorter (e.g., 'Port names are normalized...' could be integrated). Still, it's well-organized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description fully explains return values (normalized USD, confidence score, market direction) and data sources (WCI, FBX, SeaRates). It also notes it's free and indicative. Complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds meaning: explains acceptable formats for ports (city, UN/LOCODE, City, Country), container type defaults to 40ft and accepts synonyms, and reasoning behind defaults. Adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'current ocean container spot rate for a lane', and the decision-making purpose 'should I book this shipment now or wait?'. It distinguishes from the sibling tool get_lane_trend.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (transpacific, Asia-Europe, major deep-sea lanes) and when to use alternative 'For the weeks-long trend... use get_lane_trend'. Also clarifies it's indicative not a carrier quote.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It extensively discloses behavior: returns the precise point of risk transfer, who pays each step, insurance mandates, and classic traps. It also mentions it is not legal advice (regla 7), premium payment, and port normalization. No contradictions with annotations (none exist).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is thorough and well-structured, front-loading the main purpose. However, it is slightly verbose, especially with the premium payment details, but every sentence contributes useful information. It could be more concise without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of incoterms and no output schema, the description is remarkably complete. It covers risk transfer, payment responsibilities, insurance mandates, common traps, and container appropriateness. It provides all necessary context for an AI agent to use this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds value by explaining the 'incoterm' parameter values (list of rules), that 'container_type' drives a container-appropriateness check, and that 'product' is informational. This enriches the schema-provided descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool explains the exact cost and risk split for an Incoterms 2020 rule on a lane, using specific verbs and resource. It distinguishes itself from sibling tools by focusing on incoterm responsibilities, which is unique among the listed siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use this tool (when an importer makes incoterm decisions like 'FOB Shanghai' vs 'DDP my-warehouse'), and implies its value by noting that a thin agent routinely gets this wrong. It does not explicitly state when not to use or list 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.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description fully discloses that data is persisted server-side, KPIs reflect only user-recorded data with small samples flagged, and requires payment (PREMIUM). This is comprehensive for a logging tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is somewhat verbose but well-structured: core purpose first, then details, pairing with sibling, honesty note, and payment info. Could be more concise but all content is relevant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (10 params, no output schema), the description covers purpose, parameter usage, behavioral context, and return values (KPIs). Does not mention error handling or rate limits, but provides enough for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 10 parameters have schema descriptions, and the description adds meaning by grouping them (e.g., outcome includes promised vs actual days, on-time, damage). It explains how parameters feed into KPI calculation, beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it logs shipment outcomes into a private scorecard and returns running KPIs. It distinguishes itself from the sibling get_scorecard by noting it is the empirical counterpart for recording data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear usage instructions: give subject and outcome, and pair with get_scorecard for ranking. Mentions payment model but does not explicitly state when not to use or compare with other siblings beyond get_scorecard.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It thoroughly explains the three dispositions, recovery math (freight multipliers, drawback eligibility, Section 301 carve-out), storage bleed, and the indicative nature of outputs. It also notes the tool is not legal advice and mentions premium pricing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but well-structured: problem statement, required inputs, logic explanation, honest caveats. Every sentence adds value, though some sections are dense. It front-loads the core purpose and gradually details specifics, making it readable despite length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 14 parameters and no output schema, the description covers the tool's functionality comprehensively: storage bleed, drawback rules, freight multipliers, condition defaults. It lacks explicit output field names but the expected result (best disposition and recovery) is clear. For a complex tool, this is nearly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant context: how unit_value_usd drives recovery, duty_paid and section301 affect drawback, condition sets recovery/recondition, and defaults like 'rma' for condition. It explains interactions between parameters and the decision logic, far exceeding mere schema repetition.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool evaluates reverse logistics decisions (return, destroy, liquidate) and identifies the best net recovery. It specifies inputs (lane, units, value, condition) and outputs (priced dispositions). The tool is distinct from sibling tools like 'ship_decision' which focuses on forward logistics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use: for reverse flow decisions of goods returning from destination. It includes caveats about indicative results and overriding defaults. However, it does not explicitly state when not to use or point to alternative tools, though the unique purpose makes it clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: results are modeled/indicative, not audited; emission factors are bands (low/typical/high); EU-ETS cost computation details (scope, phase-in, EUA price); default assumptions (mass, container type); and premium pricing. No contradictions or hidden behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is verbose but efficiently packed with essential information. It front-loads the core outputs (WTW kg CO2e, EU-ETS cost, per-leg breakdown) and then elaborates on methodology, assumptions, and limitations. A minor deduction for length, but every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (9 parameters, no output schema, no annotations), the description is remarkably complete. It covers what the tool returns (kg CO2e, per-leg breakdown, WTT/TW split, EU-ETS cost, mode comparison), explains methodology and assumptions, clarifies exclusions (CBAM), and provides usage context (premium pricing, port normalization). No gaps for an agent to misinterpret.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds significant meaning beyond the schema: it explains that origin/dest COUNTRY drives EU-ETS scope, ship_date YEAR drives phase-in, weight_kg is recommended for accuracy, band defines reporting range, eua_price_eur overrides modeled price, and air_role distinguishes freighter vs belly. Each parameter's role in the computation is clarified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description precisely states the tool computes CO2e carbon footprint and EU-ETS carbon cost for a shipment lane. It distinguishes from siblings like compare_modes and get_spot_rate by focusing on carbon metrics rather than rates or mode comparison, and uses specific terms like 'Scope-3', 'GLEC Framework / ISO 14083', and 'WELL-TO-WAKE'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly indicates when to use this tool: for ESG reporting, EU-ETS cost calculation, and mode comparison. It also clarifies what it does not cover (CBAM taxes product, not freight) and references sibling tool 'compare_modes'. However, it does not explicitly state when to avoid using it or provide alternatives beyond the one mention.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and discloses server-side persistence, return values, alert nature (signal, not trigger), and premium pricing thoroughly.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with purpose and each sentence adds value, though slightly verbose. Still efficient overall.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (5 params, no output schema, no annotations), the description is complete: covers purpose, usage, parameters, behavior, and integration with sibling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant value by explaining each threshold metric in detail and providing examples, far beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool registers a standing watch on a lane for freight-pulse alerts, using specific verbs and distinguishing it from siblings like check_watches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
It explains when to use (for recurring alerts) and how to pair with check_watches for polling. While it doesn't explicitly say when not to use, 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.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so description fully covers behavior: normalizes to FOB base, adds assists, excludes buying commission, applies country basis. Discloses it's an indicative model, not legal advice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
Long but information-dense. Front-loaded with purpose. Every sentence adds value given complexity. Slightly verbose but acceptable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Describes return values (line-by-line base, duty comparison, deductive/computed methods). With 20 parameters and no output schema, description adequately covers what the tool does and outputs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage 100% but description adds context beyond, e.g., which parameters required for each method, how they affect calculation. Provides practical usage guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool computes the dutiable base for customs valuation, not just invoice price, using WTO methods. Distinguishes from siblings like customs_optimization by focusing on valuation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes when to use: provide destination country, invoice price, and Incoterm. Hints at alternatives (deductive, computed) and notes limitations (not legal advice). Lacks explicit when-not-to-use but informative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that inland figures are modeled market-typical bands (regla 7), not trucker quotes, and mentions PREMIUM costing (x402 on Base or prepaid key). It also notes UN/LOCODE normalization. However, it does not explain error handling, data freshness, or default behaviors for optional parameters beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence adds value. It front-loads the core purpose and then systematically details components and special cases. There is no wasted text; the length is justified by the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 8 parameters, no output schema, and no annotations, the description covers the tool's behavior well, including output (door-to-door total, p50/p90 transit). It also notes that inland adds 15-40%. However, it does not specify the exact output format (e.g., JSON structure) or handling of missing optional parameters, leaving minor gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds substantial meaning beyond the schema: it explains the role of each parameter in the door-to-door calculation (e.g., inland_destination triggers interior haul with rail-vs-truck decision, urgent biases to truck). It provides examples and clarifies defaults (e.g., inland cost band default 'typical', interior mode default cheaper of the two).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns the true door-to-door cost and time, distinguishing it from port-to-port tools. It explicitly contrasts with sibling tools like get_spot_rate, and details the components covered (inland legs, chassis, gate fees). This meets the highest standard of specificity and differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use this tool versus alternatives: 'The ocean tools price PORT-TO-PORT; this layers the INLAND legs.' It also mentions PREMIUM pricing and that inland figures are modeled bands, guiding agents on appropriate context. No exclusions are needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description is highly transparent, explaining the complex computation (RVC, tariff shift, de-minimis) and disclosing limitations (not a legal determination, risk of wrong claims). It also mentions premium pricing and links to other iter tools.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is thorough but somewhat lengthy. It is well-structured, starting with a key question and then detailing the function, examples, and warnings. Every sentence adds value, but it could be slightly more concise. Still, for the complexity, it is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 params, no output schema), the description fully explains the return values: verdict, points short, paths to qualify. It also references other iter tools for further steps. The description is self-contained and complete for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. However, the description adds significant value beyond schema by explaining each parameter's role in the FTA calculation (e.g., transaction_value is FOB denominator, materials is bill of materials). It also clarifies optional parameters like net_cost_fraction with a default value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: determining if a product qualifies for FTA preference. It explains the specific function (computing RVC, tariff shift, etc.) and distinguishes itself from siblings by mentioning links to iter4 and iter14, though it does not explicitly differentiate from other tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does 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 (checking FTA origin) and includes examples of scenarios. It does not explicitly state when not to use it, but the detailed context implies appropriate usage. No explicit alternatives are mentioned, but the sibling list suggests uniqueness.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries the burden. It discloses the cost model (capital, holding, stockout), IATA chargeable weight calculation, sea-air hub routing, and that air rates are bands. It also mentions premium payment via x402 or prepaid key.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is somewhat lengthy but well-structured: purpose first, model details, return format, payment info. Every sentence adds value, though some detail could be streamlined. It is front-loaded with the primary decision.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 17 parameters and no output schema, the description thoroughly explains the return value (table with freight, transit times, cost components, recommendation) and the decision model. It covers all necessary context for an agent to understand when and how to invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions already provide 100% coverage with clear explanations of each parameter. The tool description adds context on how parameters like 'value' and 'deadline' drive the trade-off, but the main value comes from the schema descriptions themselves.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool decides the transport mode (OCEAN vs AIR vs SEA-AIR) based on total economic cost, distinguishing it from sibling tools that price the ocean move. It uses specific verbs ('Decide the TRANSPORT MODE') and identifies the resource ('shipment').
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells when to use this tool ('answers the importer's prior question: should these goods even go by sea?') and contrasts with alternatives ('The other tools price the ocean move'). Provides context for when air/sea-air wins over ocean based on value and deadlines.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: it is modeled, simplified, non-authoritative, not legal advice, and includes payment details. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but all sentences are meaningful and well-structured. Front-loaded with core purpose, then details, then warnings. Could be slightly tighter but still effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description fully explains possible outcomes (BLOCKED, LICENCE, PERMITTED, REVIEW-REQUIRED) and the decision logic, making it complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline 3. Description adds significant meaning by explaining how parameters like product or HS code are used in the decision tree, and the classification logic.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it checks legality of export and license requirements, distinguishing it from denied-party screening. It uses specific verbs and resources, and the sibling tools list confirms uniqueness.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly defines when to use (goods-side trade compliance) and when not to use (not for denied-party screening). Also advises verification with authorities, providing clear usage boundaries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses the tool's behavior: models multiple surcharges, indicates which are included/excluded, tags values as 'typical' or 'modeled', and notes the indicative nature. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
Description is somewhat lengthy but well-structured, front-loading the core purpose. Every sentence provides value without redundancy. Minor room for tighter phrasing but overall efficient for the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 8 parameters, no output schema, and high complexity, the description is remarkably complete. It explains the return composition (line-item breakdown, all-in total, comparison) and model behavior, leaving no critical gap for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema covers all 8 parameters with 100% description, so baseline is 3. The description adds value by explaining how parameters affect cost (e.g., ship_date drives peak season surcharge, free_days/estimated_days_at_port for D&D), justifying above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns the 'ALL-IN ocean freight cost' as the true landed cost, distinguishing it from get_spot_rate which returns only the base rate. It uses specific verbs and resources, and effectively differentiates from its sibling tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs when to use this tool (for true landed cost) vs get_spot_rate (for base rate). Provides detailed context on surcharge applicability based on routes and ship dates, and mentions alternative tools implicitly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses the tool's behavior: it computes binding constraints, utilization, container comparisons, overweight warnings, and container mix. It explains limitations (indicative stowage planning, not 3D bin-packing) and mentions premium cost. This provides complete transparency for safe and correct usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but every sentence adds unique value. It is front-loaded with the purpose and structured logically: inputs, computations, outputs, and caveats. Despite its length, there is no redundancy, and the information density is high for a complex tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (10 parameters, no output schema), the description provides comprehensive coverage of expected outputs, edge cases (dense vs light cargo, overweight warnings), and container mix logic. It even includes pricing details. All essential aspects are addressed, making the tool self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, but the description adds significant value beyond parameter names and types. For example, it explains that weight_kg drives weight-binding and overweight logic, and describes how optional parameters like target_cartons or destination_country affect outcomes. This provides essential context for parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: optimizing container loading for stowage and cube/weight constraints. It specifies inputs (carton dimensions and weight) and outputs (units fit, binding constraint, utilization, container comparison, overweight warning, mix recommendation). It distinguishes itself from potential alternatives like pallet planning or load-securing certification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use (for importer's stowage/cube-and-weight questions) and provides examples (dense cargo vs light cargo). It explicitly states what it is not (load-securing certification). However, it does not directly compare to sibling tools like pallet_plan or cold_chain, which would further clarify when to choose this tool over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: scoring risk allocation, pricing LC commissions, tying to Incoterms, and noting that figures are modeled. It includes a disclaimer and mentions the premium mechanism.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is lengthy but front-loaded with the main purpose. Every sentence adds necessary detail for a complex tool. Could be slightly more concise but respects the complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 9-parameter tool with no output schema, the description covers inputs, logic, outputs, and limitations thoroughly. It explains the recommendation matrix, pricing, and ties to Incoterms, making it self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 9 parameters are described in the schema (100% coverage), but the description adds context such as the role of origin/dest ports for countries, relationship as the main driver, and default behaviors. This adds meaningful value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool recommends trade-finance/payment terms for import deals, explicitly distinguishing it from sibling freight tools. It details the payment instrument spectrum and the basis for recommendation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies when to use (for import deals) and what inputs are required (lane, invoice value, relationship). It contrasts with sibling tools and provides a clear recommendation logic based on relationship and country-risk.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: it is a modeled structural and seasonal profile, not a live depot inventory ('we never claim a specific box count is available'). It explains the underlying mechanism (equipment imbalance, seasonal swings) and pricing model (pay per call with x402 or prepaid key). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is thorough but somewhat long. It opens with a clear purpose sentence but then includes explanatory paragraphs that could be more concise. Some repetition exists (pre-CNY explained twice). However, the structure is logical (purpose → methodology → parameters → payment → alternatives), and every sentence adds value. Could be tightened slightly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 7 parameters, no output schema, and the complexity of a modeled tool, the description is remarkably complete. It explains what is returned (availability index, shortage-risk score, EIS, reposition incentives, alternatives), how to use parameters (carrier, band, ship_date), and covers edge cases (reefer pool, carrier differences, payment). No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds significant meaning beyond the schema: e.g., why origin region drives deficit (net export/import role), how container_type maps to equipment pools (40HC is tightest, 20DV easier), how ship_date affects seasonal evaluation (pre-CNY crunch, post-CNY glut), and how carrier affects availability (mega lines ease crunch). This enriches parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Check whether the shipper can even GET A CONTAINER on a lane — and what the equipment imbalance costs — BEFORE pricing the move.' It identifies the specific verb ('check'), the resource ('equipment availability on a lane'), and explicitly distinguishes from sibling rate tools like get_spot_rate, which assume a box exists.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises using this tool 'BEFORE pricing the move' and contrasts with rate tools that assume box availability. It also provides guidance on when not to use it (e.g., when live inventory is needed) and suggests alternatives within the tool (e.g., splitting container type, shifting ship window). Context for carrier and seasonal effects is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
- Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses the tool's behavior: it compares origins on total landed cost, lead time, and risk using modeled indices. It also explicitly states the limitations: 'cost indices, risk scores and lead adders are MODELED, product-specific and directional'. 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.
Conciseness4/5Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose and inputs but is quite lengthy. Every sentence adds value, covering inputs, process, outputs, and caveats. However, slightly trimming redundant phrases could improve conciseness without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (7 parameters, no output schema), the description is comprehensive. It covers required inputs, optional parameters, processing logic, and outputs (recommended origin and dual-source mix). It also notes limitations and pricing, fully preparing the agent for invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds significant meaning beyond the schema. For example, it explains that the 'fob_value' serves as a baseline for scaling other origins' costs, and that 'dest_port' determines duty/FTA treatment. This context enhances understanding of how parameters interact.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool's purpose as quantifying the strategic CHINA+1/NEARSHORING decision. It uses specific verbs like 'compares' and 'names the recommended origin', clearly distinguishing it from sibling tools like 'get_landed_cost' which likely provide only cost data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly tells the user when to use the tool: 'Give the SAME product (or HS code) + a destination market + the China-equivalent FOB cost'. It also advises that the results are modeled and directional, recommending follow-up with factory quotes and rules-of-origin checks, which is explicit usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
GitHub Badge
Glama performs regular codebase and documentation scans to:
- Confirm that the MCP server is working as expected.
- Confirm that there are no obvious security issues.
- Evaluate tool definition quality.
Our badge communicates server capabilities, safety, and installation instructions.
Card Badge
Copy to your README.md:
Score Badge
Copy to your README.md:
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Baneado98/freight-pulse'
If you have feedback or need assistance with the MCP directory API, please join our Discord server