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

Annotations cover safety (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower; the description still adds real behavioral context: alerts fire to the account's channels, alert_rule=any alerts on every move, and the traveler-confirmation gate. It doesn't state permissions beyond the confirmation requirement or what happens on repeat tracking of the same itinerary.

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 purpose and the confirmation gate, then organized by trip type, then alert behavior. It is dense and uses fragments, but every clause carries routing or behavior information; the 'any hears every move' phrasing is slightly compressed at the cost of readability.

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 tracking-creation tool with five parameters and a full output schema, the description supplies the precondition (traveler confirmation), the trip-type routing that determines the required itinerary_id, and the alert-channel semantics. Nothing an agent needs to call it correctly 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?

Schema coverage is 100%, so baseline is 3, but the description adds cross-parameter meaning the schema lacks: itinerary_id semantics differ by trip type (a one-way id watches that outbound with its cheapest return, a complete id tracks the exact pairing), and it explains how target_price_usd overrides alert_rule in operational terms.

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 ('start price alerts on an itinerary') and immediately scopes it with the precondition 'from a search, after the traveler confirms'. It is clearly distinguishable from siblings like update_flight_tracking, stop_tracking_flight, and list_tracked_flights.

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 per-trip-type routing rules for which source tool to pull itinerary_id from (search_flights vs search_return_flights), which is real 'when to use' guidance. It lacks an explicit exclusion such as 'use update_flight_tracking to change an existing alert' or a note on duplicate alerts.

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