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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorldHint=false, so the safety bar is low; the description still adds material context by disclosing that the return value is procedural guidance, not store data, and that no browser action is taken. It also explains the underlying constraint (DoorDash has no public consumer ordering API), which justifies the browser handoff. It does not state whether the account must already be logged in for the steps to apply, which is the one behavioral gap left.

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 behavior-defining clause (returns steps, opens nothing) is front-loaded, and the browser handoff follows logically. The opening clause 'from ChatGPT, Claude or any AI agent' is filler that does not help an agent decide anything, and the dated API-check footnote, while useful justification, sits awkwardly at the end.

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?

For a zero-parameter, read-only guidance tool with no output schema, the description supplies the two things an agent needs: what comes back (ordered screens/buttons/fields) and what to do next (cotlet_browser_* in the Cloud Browser). It is complete enough to invoke correctly; only the auth-state prerequisite is unstated.

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 accepts zero parameters and is fully self-describing, so there is no parameter meaning left for the description to add. Baseline for a no-parameter tool applies; nothing is misrepresented or missing.

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 (search stores in the user's own DoorDash account) and immediately clarifies the actual deliverable: step-by-step instructions with screens, buttons, and fields rather than live results. That distinction is essential because the name alone would suggest it performs the search. It stops short of differentiating against near siblings such as doordash_read_store_menu, so it is clear but not fully disambiguating.

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 gives explicit sequencing: call this to get the steps, then carry them out with cotlet_browser_* tools in the user's DoorDash Cloud Browser, and it states plainly that the tool 'opens nothing by itself.' That is a usable when-to-use contract. There is no stated exclusion case (e.g., when a different DoorDash tool already answers the question), but no incorrect guidance either.

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