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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the write/open-world profile is known. The description adds real context beyond that: the 24-hour submission window, the default per-call confirmation, the 'reaches other people' external effect, and the API-key access requirement. A minor gap is that it does not say whether re-sending documents replaces or appends existing entries.

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 action and purpose, then layered with timing, sourcing, and confirmation rules. Every sentence carries operational information, though the density of behavioral rules in the tail makes it slightly dense for a single description.

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 still covers everything an agent needs for a mutation tool: what is written, the timing constraint, the parameter sources, the confirmation default, the external reach, and the auth requirement. Nothing material is left for the agent to infer.

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 goes beyond the schema by tying each parameter to its source: details comes from get_trip's documents_needed list, and it implies trip_id/passenger_id come from list_trips/get_trip, which adds meaningful provenance the schema alone doesn't state.

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 ('Add the passport or ID details') and clarifies the downstream purpose: Kiwi.com passes them to the airline for check-in. This is clearly distinguishable from siblings like kiwi-com_get_boarding_passes or kiwi-com_select_seat, and an agent can tell what gets written 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 explicit when/when-not guidance ('up to 24 hours before departure; later you check in with the airline') and routes the agent to get_trip for the required fields ('Send the fields get_trip lists under documents_needed'). It also states the confirmation default and that it reaches other people, so the agent knows the interaction pattern.

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