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

With annotations already declaring openWorld, idempotent, and non-destructive, the description adds real value: it explains the idempotency key's recovery purpose, enumerates what the call will NOT do (prepare/confirm/pay/cancel/change), and states that options are returned to the original conversation. It does not explain what the 'search limit' or 'expiry' constraints actually mean in practice.

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?

Four short sentences and the negative scope is front-loaded well, but the opening sentence is densely packed and awkwardly worded, forcing the reader to parse 'separately approved exact-order permission, expiry and search limit' as three separate constraints.

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 tool with four required parameters, a nested slices schema at 0% description coverage, and no output schema, the description leaves the agent unable to construct a valid call without guessing at handoff_id/permission_id provenance and the remove/add slice semantics. The behavioral side is reasonably covered, but the input contract is not.

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 description coverage is 0% and the schema contains a nested slices object with remove/add arrays, yet the description never explains handoff_id, permission_id, or the structure of slices. The only parameter-level insight is the idempotency-key recovery behavior, which does not compensate for three undocumented required parameters, one of which is a nested object.

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+resource ('Query change offers') scoped to a travel-change context, which clearly separates it from evuun_search_flights and evuun_propose_travel_change. The qualifier 'within the separately approved exact-order permission, expiry and search limit' is grammatically tangled but signals the tool is bounded by a pre-approved permission scope.

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?

The exclusions ('does not prepare, confirm, pay, cancel or change a ticket') implicitly route the agent away from evuun_propose_travel_change and payment siblings, and the idempotency-recovery sentence gives one concrete operating rule. However, no positive guidance is given on when to call this versus evuun_get_travel_change_context or evuun_prepare_travel_handoff, and the 'separately approved permission' prerequisite is only alluded to.

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