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

Annotations already establish readOnly/idempotent/non-destructive, and the description goes well beyond them: it says nothing is posted, no booking or charge occurs, Seat Sherpa is unaffiliated with the providers, and one member books in their own app while others pay directly. It also describes the downstream flow (sign-in, fare estimate, per-person share, posting) so the agent knows what the returned link exposes.

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 definition and trigger before the mechanics and disclaimers, and every sentence carries information. It is on the long side, with the unaffiliated/no-booking disclaimer taking a full sentence, but no sentence is pure 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 four-parameter link builder with no output schema, it covers the return value, the no-side-effects guarantee, and where responsibility for booking lies — everything needed to call it safely. The only missing piece is how it relates to searching for existing cabpools versus posting a ride link.

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; the description earns more by explaining what the parameters do downstream — the link opens the form with pickup, drop-off and day pre-filled, and the day can be left for the person to choose. It does not mention the optional time parameter, so it does not fully mirror 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 concrete verb and artifact ('builds the link') plus a precise, distinguishing resource definition: sharing an Uber/Lyft/Waymo ride and splitting the fare, typically to or from named airports. Explicitly contrasts with search_rides for short intra-area trips, so an agent can route without opening any 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 trigger ('use it when the person wants to split a rideshare rather than ride in someone's car') and an exclusion against search_rides. It does not differentiate from the closer siblings search_cabpools, post_ride_link or request_ride_link, which is the one routing gap.

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