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

Annotations already cover read-only, idempotent, non-destructive and non-open-world, yet the description still adds real value: consent gating, termination on expiry/revocation/identity change, and an explicit list of data it will not expose (traveler details, ticket identifiers, payment secrets, supplier queries, financial actions). That disclosure of scope limits and lifecycle failure modes goes beyond what the annotations declare.

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 and terse, with the scope and consent gate first. However, the 'caller_task_ref' sentence is dead weight at best and confusing at worst, since that identifier is not accepted by the schema.

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?

The access-control and data-minimization picture is well covered, but with no output schema and no handoff_id documentation, an agent still does not know what a 'travel progress' response contains or how to obtain a valid handoff_id. Enough to invoke safely, not enough to use confidently end-to-end.

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 sole parameter, handoff_id (with a strict pattern), is never explained in the description. Worse, the description references 'caller_task_ref', which is not a parameter of this tool, adding a misleading pointer instead of clarifying handoff_id.

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 clear verb and resource ('read... one selected travel order') and scopes it precisely to this connection's single order, which separates it from list-style siblings like evuun_list_commerce_progress. It never names a specific sibling, so differentiation is only implied.

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?

'after explicit owner consent' establishes a precondition, but there is no explicit when-to-use/when-not guidance relative to siblings such as evuun_get_travel_change_context or evuun_list_commerce_progress. The instruction to 'continue in the original conversation using caller_task_ref' describes a workflow step rather than selecting this tool over an alternative.

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