ue_policy

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

With no annotations, the description carries the disclosure burden and does well: 'Read' implies a safe, non-mutating call, and it reveals the surprising environmental dependency on Uber Eats being logged in via Chrome, plus that caps are expressed in the account's currency. It omits failure modes (e.g., what the tool returns when logged out) or rate-limit behavior, which 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?

Two compact parts: a front-loaded enumeration of the returned fields followed by a single tiered bullet with the usage trigger. No sentence is padding, and the most decision-relevant information (caps, spend, login state) comes first.

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?

Because there is no output schema, the description must describe the return payload, and it does so field by field, including the login-state value an agent may need to branch on. It doesn't cover what happens when ordering is disabled or when Chrome isn't logged in, leaving a small behavioral gap for a tool whose whole purpose is gating downstream actions.

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?

The schema has zero parameters, so the baseline is 4 per the rubric. Nothing in the description contradicts or adds parameter meaning, and none is needed.

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 ('Read') and resource ('the ordering policy') and then enumerates exactly what the policy contains: enabled flag, per-order/per-day caps, today's spend, and Uber Eats Chrome login state. This is clearly distinguishable from siblings like ue_add, ue_cart, and ue_place, which mutate or inspect cart/order state rather than policy limits.

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 'Use this when' block gives an explicit trigger: before adding to cart or placing an order, check the caps. It clearly signals the pre-flight role relative to ue_add and ue_place, but does not name those siblings or state when this tool is unnecessary, so it stops short of full routing guidance.

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