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

Annotations already cover read-only, non-destructive, open-world, so the bar is lower; the description still adds real value by disclosing that this performs two underlying GET calls and under what state conditions the second fires. It stops short of noting what happens when no driver is assigned beyond the implicit 'no driver data'.

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 with the user-facing question and what comes back, then the call mechanics. Two sentences, no filler; the endpoint paths are slightly technical but justify themselves by explaining the conditional second read.

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 return-value burden and does name the key fields (status, POD, share link, driver name, live coordinates). For a single-parameter read tool this is nearly sufficient, though the absence of any contrast with lalamove_get_order leaves a selection ambiguity.

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?

Only one parameter with 100% schema description coverage, so the schema fully documents order_id including its pattern. The description adds no extra semantics about the id format or accepted values, so the 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?

Opens with a concrete question-form purpose and enumerates exactly what is returned: order status, stop-level proof of delivery, share link, and conditional driver name/coordinates. The verb 'track' plus resource is clear, but it never distinguishes itself from the sibling lalamove_get_order, which likely overlaps heavily.

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 an explicit condition for the extra driver read ('if a driver is assigned and the order is ON_GOING or PICKED_UP'), which tells the agent what to expect rather than how to choose the tool. No guidance on when to pick this over lalamove_get_order or how it relates to cancel/change_driver.

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