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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false; the description valuably corroborates this by stating the tool 'opens nothing by itself' and only emits instructions, which prevents an agent from expecting a side effect. It also discloses the notable constraint that DoorDash has no public consumer ordering API. Minor noise: the 'checked 27 Oct 2026' provenance stamp is stale/future-dated detail that adds little.

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 core de-confusing fact ('opens nothing by itself') is front-loaded, which is good. But the single dense sentence chains four ideas with semicolons and appends an API-absence claim and a date stamp that belong in background documentation rather than the operative description.

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 does its job by telling the agent the return value is step-by-step screens/buttons/fields. Combined with annotations and the stated follow-up path through cotlet_browser_*, an agent knows enough to invoke it correctly, though the missing explanation of the zero-parameter design and the lack of a clear hand-off to doordash_submit_order leave small gaps.

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?

Zero parameters means there is no schema semantics to compete with, which would normally be a 4 baseline. But the absence of any item or option parameter is unexplained: the description never states how the item to add is determined (presumably from conversation context or a prior doordash_read_store_menu call), leaving a real ambiguity for an 'add item' operation.

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 names a specific verb and resource ('Add item to cart in the user's own DoorDash account') and immediately clarifies that the tool returns step-by-step instructions rather than performing the action. That reframing is what distinguishes it from what the name implies. It does not explicitly contrast itself with doordash_submit_order or doordash_preview_order_total_with_fees, so it stops short of full sibling differentiation.

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?

It says what to do next ('then do it with the cotlet_browser_* tools in the user's DoorDash Cloud Browser'), which is useful sequencing guidance. However, it never says when to prefer this over doordash_submit_order, doordash_preview_order_total_with_fees, or doordash_read_store_menu, and gives no precondition such as needing the cart/options already selected or a browser session opened.

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