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

Annotations already declare destructiveHint=true, but the description goes far beyond them: no undo, a working register taken out of service, the device needing re-provisioning in the POS app, and the station returning as a new object with a new id. It also explains the IN_USE refusal semantics and that past orders, sessions and End of Session reports are preserved.

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?

It is front-loaded with the action and then layers confirmation and edge-case handling in logical order. The IN_USE and stale-flag discussion is dense and runs a little long, but nearly every sentence carries actionable information rather than filler.

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 destructive, no-undo tool with one parameter and no output schema, the description supplies everything an agent needs: the scope of destruction, the refusal condition, recovery guidance for a stale flag, and the reassurance that historical records are untouched.

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 the single parameter already documents 'Station id from get_stations — not a name.' The description restates the same source but adds no format, syntax, or edge-case detail beyond the schema, 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?

The description states a specific verb and resource ('Remove a till from Run → Stations') and pins down the exact object via 'Takes the station id from get_stations.' An agent can immediately distinguish this from hub_create_station and hub_rename_station among the siblings.

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 when-to-apply rules: confirm with the merchant first, the deletion is refused while the station reports IN_USE (close the shift on the device first), and if the flag is stale, wait for reconnection rather than forcing. This covers usage, prerequisites, and exclusions better than most definitions.

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