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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this by stressing the plan is only a proposal until cxt_save_order_plan. It also adds non-structured context: the ITINERARY_PLANNING_ACCESS permission requirement and the prerequisite call to cxt_get_planning_limits. Missing rate-limit or planning-window constraint details keeps it from a 5.

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 proposal semantics and the 'only PROPOSES' warning, then layers permissions, prerequisite, and endpoint. No filler sentences; each one adds a distinct operational fact.

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 compensates by outlining the returned itinerary contents (sequenced stops, times, distance, unassigned stops), and it covers auth scope and the prerequisite limits call. An agent has everything needed to invoke this correctly.

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 88%, so nearly every parameter is documented in the schema, and the description adds no syntax or format detail beyond it. Its mention of 'pickup and delivery stops in sequence, with times, distance and unassigned stops' describes the response rather than parameter semantics. Baseline 3 applies.

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: 'Generate a proposed itinerary that assigns on-demand orders to drivers', and enumerates the output shape (sequenced stops, times, distance, unassigned stops). This lets an agent distinguish it from cxt_plan_routes and cxt_optimize_order_plan without opening any 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?

Explicitly states the tool only proposes and that nothing is dispatched until cxt_save_order_plan is called, and it directs the agent to call cxt_get_planning_limits first. It does not contrast with cxt_plan_routes or cxt_optimize_order_plan, so the sibling-selection guidance is incomplete but otherwise clear.

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