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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description does add useful scope context — 'typical Uber and Lyft prices in New York' signals an estimate rather than a live quote and a NYC-centric coverage — plus that the result carries actionable links. It stops short of stating latency, freshness, or geographic limits outside NY beyond the one reference.

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?

It is a single sprawling sentence built from a long comma list of outputs, with no front-loaded statement of the action. It is not padded with filler, but the structure buries the tool's core function behind an inventory of return values.

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, enumerating what comes back (distance, time, meter fare, flat fares, Uber/Lyft estimates, links) is genuinely useful. However, for a 4-parameter open-world tool it omits the selection context versus fairfare_check_fare and any note on accuracy or coverage limits, so it is only adequate.

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 from/to/city/when are fully documented in the schema and the baseline is 3. The description adds at most a faint signal for 'when' via 'the extras that apply at that hour', and nothing for city or the accepted place formats.

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 title and opening frame the tool as 'what a trip should cost by taxi, Uber or Lyft', but the description body is a comma-run of return contents rather than a stated action ('estimates the fare between two places'). It also never distinguishes itself from the very similar sibling fairfare_check_fare, leaving the agent to guess which to call.

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?

There is no when-to-use guidance at all: no mention of fairfare_check_fare, fairfare_best_time_to_ride, or fairfare_get_taxi_tariff as alternatives, and no statement of when this estimator is the right choice over tariff lookup. The only implicit cue is that inputs are two places.

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