Seatac Connection rides

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

Annotations already declare readOnly/idempotent/closed-world, so the safety profile is covered. The description adds non-obvious behavior beyond that: the default no-date behavior restricts results to today onward, and turnaround days embed a ride_to_pier object with a prefilled booking link and quote_ride_arguments. No output schema exists, so it would benefit from slightly more on the shape of returned records (e.g. what fields exist for non-turnaround days).

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

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

Front-loaded with the core purpose, then filtering, then the cross-tool workflow, then the default-date caveat. Sentences are information-dense with no filler; the only mild cost is that several ideas are packed into long parenthetical clauses.

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, 6-param, all-optional query tool with no output schema and no nested objects, the description covers what it returns (pier/terminal, ships per day, ride_to_pier booking data) and the default date behavior. A little more on the response structure would make it fully complete.

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

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

Schema description coverage is 100% with per-parameter descriptions and an enum for pier, so the schema already does the heavy lifting. The description restates the filter set and adds the fuzzy-matching hint for ship, but that hint is also in the schema, so little value is added beyond it.

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

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

Specific verb+resource: 'Look up Seattle cruise sailings from the Port of Seattle schedule', with the exact queryable facts (pier/terminal per date, ships per day) and season scope (2026 + preliminary 2027). It is clearly distinct from siblings like quote_ride, which it names as a downstream step.

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 concrete filter dimensions (ship fuzzy, cruise_line, date or from/to, pier) and a clear hand-off rule: call quote_ride with quote_ride_arguments plus a pickup time for the live fare. Also states the implicit default ('without a date filter, only sailings from today on are returned'), which governs when a date filter is needed. No explicit 'do not use this for X' exclusion, keeping it at 4.

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

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

Annotations already declare this read-only, idempotent, and closed-world, so safety is covered. The description adds useful context by enumerating the categories of information returned and clarifying that fares here are per-trip quotes, not live prices.

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

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

Three sentences, each carrying distinct information: service identity, return contents, and the quote_ride redirect. There is no redundancy or filler.

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

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

For a zero-parameter informational tool with read-only annotations and no output schema, the description fully covers what an agent needs: what the tool returns and where to go for pricing. Nothing material is missing.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate. The baseline for a parameterless tool is 4, and no parameter-related confusion is possible.

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

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

The description states precisely what the tool returns: service area, vehicle types with passenger/bag capacity, booking requirements, and cancellation/refund policy. It also distinguishes the tool from quote_ride, making the boundary between static service information and live pricing explicit.

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

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

It explicitly routes price inquiries to quote_ride, which is the main ambiguity an agent would face among these siblings. It does not explicitly state when to call this tool (e.g., before booking or for policy questions), leaving that to be inferred from the listed return contents.

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

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

Annotations already declare readOnly, idempotent, closed-world; the description adds genuinely new behavior: rate limiting, per-eligible-vehicle fan-out, and that pricing mirrors seatac.co checkout exactly. It doesn't say what happens when no vehicles are eligible or how stale a quote can get, but the value-add over annotations is real.

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

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

Three sentences, front-loaded with the verb and resource, then the return shape, then the rate-limit constraint. Nothing is redundant with the title or schema.

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

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

With no output schema, the description usefully sketches the response (one entry per eligible vehicle, each with a booking_url for review and payment). Remaining gaps — what fields besides booking_url a quote contains, and fallback behavior when nothing is eligible — are minor for a quote tool.

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

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

Schema coverage is 100% and each parameter already carries a description with examples and ranges, so the description does not need to compensate. It adds only indirect hints ('per eligible vehicle', hourly charter implied via the hours param) and no format or constraint detail beyond the schema.

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

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

States a specific verb and resource ('Get the live fare for a specific Seatac Connection ride') with scope qualifiers: per eligible vehicle, priced as seatac.co checkout. An agent can tell this is the pricing step as opposed to the sibling start_booking, which actually books.

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 explicit operational guidance: reuse a quote instead of re-requesting it because the tool is rate limited. It implies this is the step before booking (each vehicle carries a booking_url), but it never explicitly says 'call this before start_booking' or states exclusions.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, but the description adds genuinely useful context: the tool produces a link, the customer completes contact details and payment off-tool, and nothing is booked or charged. It does not say whether the link expires or can be reused, which is the remaining behavioral gap.

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

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

Three short sentences with no waste. The core action is front-loaded, and the follow-up sentences explain the handoff and the no-charge guarantee. Every sentence earns its place.

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

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

With eight parameters, full schema coverage, no output schema, and annotations covering safety, the description is nearly complete for the agent's needs. It conveys what is produced (a link) but does not state the response shape explicitly, which would have been helpful given the absence of an output schema.

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

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

Schema description coverage is 100%, so every one of the eight parameters is already documented with examples and ranges. The description adds no parameter-level meaning beyond describing the overall trip-review flow; baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description gives a specific verb and resource: create a prefilled seatac.co reservation link. It is clearly not a booking or payment tool, which distinguishes it from a charging action. It does not name any sibling tool (quote_ride, get_service_info) as the alternative for pricing or vehicle selection, so sibling differentiation is only implicit.

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

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

Usage is implied rather than stated: the agent can infer this is the step where the customer is handed off to seatac.co to review and pay. There is no explicit 'use this after quote_ride' or 'do not use this to obtain prices' guidance, and no mention of when to prefer it over the sibling tools.

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