Seat Sherpa

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, and 'Read-only' merely echoes them. The description does add genuine context beyond the structured fields: departure times are in Pacific time, prices are all-in USD per seat, and the returned set includes driver rating, trips, note, flexibility and cancellation policy.

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

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

Purpose and id provenance are front-loaded, then the returned fields are enumerated in one dense sentence. The enumeration is long but justified because there is no output schema; nothing reads as filler.

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

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

With no output schema, the description carries the return-value burden and does so thoroughly (route/stops, times, seats, price, driver info, note, flexibility, cancellation policy, booking link). Parameter origin, read-only nature, and timezone/currency units are all covered.

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

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

Schema coverage is 100% and the single parameter is documented there as 'The ride id.', so the schema does the heavy lifting. The description adds meaningful provenance beyond the schema by specifying the two places the id can be obtained, which prevents the agent from guessing.

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 ('Public details of one Seat Sherpa ride by its id') and distinguishes itself from search_rides by naming it as the id source. An agent can tell it apart from list_service_areas, post_ride_link, and request_ride_link immediately.

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 tells the agent where the ride_id comes from ('from search_rides or a seatsherpa.app/ride link'), which is clear routing from the sibling tool. It does not state when not to use it or what to do if the id is unknown, so it stops short of explicit when/when-not guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real domain scope (CA/NV coverage) but says nothing about the freshness or form of the data returned, which is the main behavioral question for a reference-data lookup.

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

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

Two short sentences, no redundancy, with the scope statement front-loaded before the usage instruction. Every clause earns its place.

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

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

For a zero-parameter, no-output-schema lookup, the description supplies what matters: what the data covers and when to consult it. The only gap is that it never hints at the shape of the result (e.g. list of area names or IDs), which an agent would have to discover empirically.

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 baseline there are no parameter semantics to explain. There is no risk of misusing an argument and no schema detail the description needs to compensate for.

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

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

Names the concrete resource (the California and Nevada areas Seat Sherpa carpools run between) and makes its scope explicit. It is distinguishable from siblings like search_rides or get_ride, though the verb is implicit 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?

Gives a clear usage rule: 'use it to check whether a trip is covered before searching,' establishing the precondition for search_rides. It does not name that sibling explicitly or describe what to do if the trip is not covered, so it stops short of full alternative routing.

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

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

Annotations already cover readOnly/idempotent/non-destructive/openWorld, and the description adds meaningfully on top: 'this tool only builds the link and posts nothing,' plus the split of responsibility ('the driver signs in and posts on the page'). It stops short of describing link format or validity, so not a 5.

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

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

Front-loads the core purpose and the when-to-use/when-not contrast in the first two sentences, with the important 'posts nothing' caveat last. Slightly padded by the marketplace color ('riders share costs like gas and tolls'), which does not aid tool selection.

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 3-param, no-output-schema link-builder, the description covers the persona trigger, the non-mutation behavior, and the handoff to the driver on the page. Only the nature of the returned value (how the link is delivered/used) is left implicit.

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

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

Schema description coverage is 100%, including date parsing rules and today's date, so the schema does the heavy lifting. The description only restates 'takes the starting place, the destination and an optional date' without adding format or constraint detail beyond it. Baseline 3 applies.

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

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

States a specific verb+resource (build a link for a driver to post a drive) and makes the driver-vs-rider distinction explicit, which cleanly separates it from request_ride_link and search_rides. An agent can route correctly 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 an explicit when-to-use trigger with a concrete user utterance example ("I'm driving to LA on Friday, can I take people?") and an explicit when-not ("not to find a ride"). The driver persona condition is the exact discriminator against 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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld. The description adds valuable context beyond them: this tool only builds the link, posts nothing, requires the person to sign in and post on the page, and never needs names, phone numbers or emails. This is meaningful side-effect and privacy disclosure.

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 purpose and the usage condition efficiently in a single dense paragraph with no filler. It is slightly long, but each sentence carries functional information.

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

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

No output schema exists, yet the description explains that the result is a link the person uses on the page and that nothing is posted by the tool. Combined with full param coverage and rich annotations, an agent has everything needed to call it correctly.

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

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

Schema description coverage is 100%, so the schema already documents from, to, date and seats semantics in detail. The description adds only a high-level hint that it takes the same places and optional date as search_rides, so baseline 3 applies.

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

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

States a specific verb and resource: it builds a link where a rider posts a ride request on the Seat Sherpa carpool marketplace. It clearly distinguishes itself from search_rides (which finds existing rides) and from post_ride_link by naming the rider-side flow.

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 trigger conditions: use it after search_rides finds nothing, or when the person wants to be notified about an unposted trip, and it notes that search_rides already includes this link. That is exactly the when-to-use routing an agent needs.

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

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the description is free to add the operationally interesting traits: stop-over matching semantics, Pacific timezone, price inclusive of fees, and the explicit constraint that booking cannot happen here. Nothing contradicts the annotations.

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

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

Front-loaded with the core purpose and invocation inputs, then returns, then the booking caveat. The parenthetical "(the same link request_ride_link gives)" is redundant, and the second paragraph is dense, but every other sentence carries information.

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

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

There is no output schema, so the description correctly carries the return-value burden (route, departure time zone, seats left, all-in USD price, driver first name, booking link). Combined with date handling and the no-result fallback, an agent has everything needed to call and interpret this 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%, so the baseline is 3, but the description adds real matching semantics beyond the schema: that a ride stopping in a city counts for that city ("a San Jose to San Diego ride with a Los Angeles stop is found for Los Angeles to San Diego"), which directly affects how from/to values are interpreted.

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?

Opens with a specific verb and resource ("Find upcoming long-distance carpool rides on Seat Sherpa") and scopes the domain to California and Nevada. It also implicitly separates itself from siblings by noting it returns a list and cannot book, unlike get_ride or post_ride_link.

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

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

Gives clear invocation context (supply from/to city or place names, optional travel date) and handles the no-results case by routing to request_ride_link. It does not, however, explain when to prefer get_ride or list_service_areas over this search, so sibling differentiation is only partial.

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