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

Annotations already declare readOnlyHint and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral value beyond that: the day-by-day return shape, ordering of places, and the auth requirement (Cotlet API key with access to this app), which the agent needs before invoking.

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 return shape and scopes it in a few tight sentences. Minor redundancy between 'Returns the itinerary day by day' and the opening 'Full itinerary: days,' but overall efficient with little wasted space.

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 burden of describing the return value, and it does so reasonably well (days, places, times, notes, hotels, reservations, lists). It also flags the auth prerequisite. Pagination or size limits for large trips are not addressed, leaving a small gap.

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%, with 'day' and 'trip_id' both documented in the schema, so the baseline is 3. The description restates that 'day' returns one day only, which is redundant with the schema's own 'Return only this day' description and adds no new syntax or format detail.

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 (get) and resource (trip itinerary), and enumerates exactly what the itinerary contains: days, places with times and notes, hotels, reservations, lists and checklists. An agent can distinguish this from wanderlog_list_trips or wanderlog_list_expenses without opening a 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 concrete usage context: 'Pass day to return one day only,' and routes the agent to a sibling by explaining that each place carries a block_id for remove_place. It stops short of explicitly naming when to prefer this over list_trips, so it is clear context without full alternatives.

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