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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuine context beyond that: the result is a live snapshot of open orders only (not history), and it is scoped to the driver's manifest. It says nothing about result size or how a driver is resolved when both keys are absent, but for a read-only lookup this is solid.

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?

The scope statement and field list are front-loaded in a single dense sentence, followed by the exactly-one constraint—efficient and well ordered. The trailing "GetDriverInfoFromDriverCode / GetDriverInfoFromDriverPhone" reads as leaked internal method names, adding tokens without adding actionable meaning for an agent.

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?

There is no output schema, so the description carries the return-value burden, and it does describe the shape of a result row. Given only two flat string parameters and read-only annotations, that covers nearly everything needed; minor gaps are how errors surface when the driver is unknown and whether multiple manifests could contribute orders.

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% and both fields are self-describing, so the baseline would be 3. The description earns an extra point by imposing a constraint the schema does not encode—required is empty and there is no oneOf/anyOf, yet the description mandates exactly one of driver_code or driver_phone, which prevents an ambiguous or empty lookup.

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?

The description gives a concrete verb and resource—the open orders currently on a driver's manifest—and enumerates the returned fields (customer, pickup/delivery names, delivery zip, ready and due times). That framing cleanly separates it from siblings like ecourier_get_manifest and ecourier_list_driver_manifests, which deal with the manifest itself rather than the driver's live order load.

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?

"Give exactly one" tells the agent how to select between the two lookup keys, which is real usage guidance. However, it never states when to prefer this tool over ecourier_get_manifest, ecourier_list_driver_manifests, or ecourier_get_driver, so the agent must infer the boundary from the purpose sentence alone.

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