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

Annotations already flag destructive/idempotent, but the description adds real substance: the key is immediately invalidated and discarded, the widget/query/dashboards are untouched, the address is retained for republishing, no-op on unpublished widgets, and required roles (owner/admin/editor). It also discloses the not-found error text.

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 action and its immediate consequence, followed by collateral effects, idempotency, return shape and permissions. Dense but every sentence adds information an agent would otherwise have to guess.

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?

No output schema exists, yet the description spells out the return shape (widgetId, name, published: false), the authorization requirement, and the error case, which is everything needed to invoke and interpret the call.

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 both parameters are documented in the schema (including which list tools supply the ids), so the schema carries the load; the description adds no further parameter-level detail. 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?

States a specific verb and resource ('Turn off a widget's private web address') and explicitly ties it to the inverse sibling fastero_publish_widget_api, so it is distinguishable from any other mutation tool in the list.

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?

Clear context: use it to sever the published API key, and the counterpart publish tool is named as the way back. It also says what happens for an already-unpublished widget, but it does not contrast against other options such as deleting the widget entirely.

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