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

Beyond the annotations (destructiveHint, idempotentHint, readOnlyHint=false), the description discloses real behavioral consequences: an empty defaults list is valid, prompts without an override run globally, existing prompt overrides are left untouched and may still select the region, and the allowance is computed as the union of defaults and enabled overrides. This is exactly the side-effect detail an agent needs before invoking a destructive mutation.

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?

Five short sentences, front-loaded with the action and each conveying a distinct behavior (defaults validity, override immutability, allowance semantics, return, no scan launch). Slightly dense but no 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 mutating tool with annotations covering the safety profile and an output schema covering the return payload, the description adds the remaining decision-critical context: what is preserved (prompt overrides), what the result is, and that no scan is triggered.

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 50%: siteId is documented as 'Site or Topic ID from list_sites_and_topics', region is only typed as a string. The description adds partial meaning by clarifying that region is a 'region ref' and may be an 'obsolete ref', but gives no format or source for valid values, so it only partly compensates.

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 ('Remove a region ref ... from the Site/Topic scan defaults') and scopes the effect precisely, including that it does not launch a Scan, which separates it from trigger_scan. It never names the inverse sibling add_scan_region, so the differentiation is implicit rather than explicit.

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?

Usage is implied by the semantics (use it to drop a region from Site/Topic scan defaults) and the 'Does not launch a Scan' note scopes it away from scan execution. However, there is no explicit when-to-use/when-not guidance or routing to add_scan_region for the opposite operation.

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