Othermile border costs

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

readOnlyHint=true already covers the safety profile, so the description is free to add value — and it does, disclosing that results come from real reports and are only returned when a sufficient number of reports exist (a gating/empty-result behavior not visible in the schema). It stops short of describing aggregation, freshness, or how sparse data is surfaced, so it's short of a 5.

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

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

Two tight sentences, purpose front-loaded and the availability caveat placed second where it belongs. No filler, though the phrasing is conversational rather than maximally information-dense.

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

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

For a read-only, 3-parameter tool with no output schema, the description conveys what data is returned (amounts paid, durations) but not the structure of the result or how the optional 'from'/'mode' narrow it. Adequate but leaves an agent guessing at the response shape and parameter effects.

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

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

Schema description coverage is 33% — only 'from' is documented; 'to' and 'mode' rely on bare enums. The description adds nothing about route direction ('to' required, 'from' optional), what each parameter means, or how mode affects results, so it fails to compensate for the coverage gap.

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

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

States a specific resource (empirical cost and transit-time outcomes for a route) and verb is clearly retrievable, with 'actually paid'/'actually took' distinguishing it from quote-style siblings. It never names border_quote or door_cost_estimate explicitly, so the contrast is implied rather than stated.

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

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

The 'actually paid ... actually took ... from real reports' phrasing implies this is for historical/observed data rather than forward-looking estimates, which weakly routes against border_quote and door_cost_estimate. There is no explicit when-to-use, when-not-to-use, or named alternative, and the sample-size note is a caveat rather than usage guidance.

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

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

Annotations already mark this as readOnly and closed-world, so the description need not establish safety. It adds that the tool estimates rather than quotes, enumerates the charge categories, and covers bans, Incoterm payer, and exporting-country requirements, which usefully sets output expectations. It omits any accuracy, currency, or non-binding-disclaimer context.

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

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

Three compact sentences, front-loaded with the core action and ending with a clear usage cue. No filler or repetition of schema fields.

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

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

For a complex 11-parameter estimator with nested items and no output schema, the description explains the high-level return categories but not the structure of results or key limitations. The schema carries most input detail, so it is serviceable, but the missing output/limits context leaves a gap.

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

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

Schema description coverage is 82%, so the schema already documents most inputs in detail. The description only broadly gestures at modes ('parcel or freight') and mentions Incoterm/bans, without adding syntax, defaults, or item-level meaning beyond the schema.

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

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

Specific verb 'Estimate' and resource list (duties, tariffs, taxes, fees, bans, Incoterm payer) distinguish it from a generic quote tool. But it does not name or contrast with sibling border_lane_insights, border_rules_status, or door_cost_estimate, so sibling differentiation is absent.

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

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

Provides a clear timing cue: use before buying from or shipping across the border. That frames the use case, but it gives no when-not conditions and never routes the agent to or away from the sibling tools.

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

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

readOnlyHint=true already establishes this is a safe read, so the bar is lower. The description does add genuine context annotations don't carry: that each list's provenance is reported ('whether each list has been checked against the official text'), which tells the agent about data freshness/reliability. It stops short of describing scope, coverage, or refresh cadence.

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

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

A single front-loaded sentence that opens with the scoping condition ('which rules are in force right now') before listing contents. No filler, though the dense comma-list of returned fields reads slightly like an inventory rather than prose.

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

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

With no parameters and no output schema, the description carries the burden of conveying the return payload, and it does so by naming the four things returned. It does not describe the response shape or format, but for a simple zero-arg status read that is a minor gap.

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

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

The tool takes zero parameters, so per the rubric the baseline is 4. Nothing in the schema needs additional explanation and the description correctly spends no effort on arguments.

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

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

The description names the specific resource (Canada/US border rules currently in force) and enumerates the payload it covers: tariff measures, rates, start dates, and verification status. It is clearly distinguishable from border_quote and door_cost_estimate, though it never explicitly contrasts itself with siblings and is framed as a content list rather than a verb+resource action.

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

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

The phrase 'in force right now' implies the temporal use case (current-state lookups) but there is no explicit when-to-use guidance, no exclusions, and no mention of the sibling tools. Usage is only implied.

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

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

Annotations only declare readOnlyHint and openWorldHint=false, so this is a safe local computation. The description adds real context beyond annotations: the estimate uses 'official rules in force today' (time-sensitivity) and the tariff code is auto-suggested from the plain-word product description rather than required. No auth, rate-limit, or error behavior is described.

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

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

Front-loads the cost scope in the first sentence, then the input guidance, then a concrete example. Three sentences with essentially no waste, though the example could arguably be folded in.

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

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

For a 10-parameter read-only calculator with no output schema, the description conveys what is computed, the rules basis, and the key input convention. It does not explain what the returned estimate looks like (only a number? a breakdown?), which is the main residual gap given no output schema.

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

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

Schema coverage is high (90%), so the baseline is 3, but the description adds meaning beyond it by clarifying the relationship between 'product' (plain words) and 'tariffCode' (optional, only if known, otherwise suggested) and by hinting the product description drives the code lookup.

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

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

States a specific verb (estimate) and resource (door/landed cost for one parcel) with explicit scope: CA-US cross-border, covering duty, tariffs, surtaxes, sales tax and carrier fees. An agent can distinguish this from border_rules_status or border_lane_insights without opening the schema.

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

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

Gives a concrete when-to-use cue via the shopper example ("what will I pay on a hoodie from a US store shipped to Ontario?") and instructs 'describe the product in plain words'. It does not explicitly name sibling tools or exclusions, so routing versus border_quote is left to inference.

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