viewer_isolate

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

Annotations declare destructiveHint=true, and the description usefully clarifies the semantics of isolation (that everything else becomes hidden), which is meaningful context for a mutation of viewer state. It does not, however, say how to restore visibility (viewer_clear/viewer_fit) or that isolation replaces prior visibility state.

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?

A single, front-loaded sentence with zero wasted words, and the parenthetical definition is placed immediately where it is needed.

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?

An output schema exists, so return values need not be explained. For a one-parameter viewer operation the description is largely adequate, though it omits the prerequisite of an open viewer and the interaction with sibling viewer operations.

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 description coverage is 0% and there is one parameter, so the description must compensate. It names the parameter (pnt_ids) and implies its meaning (point/entity IDs to keep visible), but provides no format, source, or behavior when the array is empty. Baseline 3 is appropriate given the partial compensation.

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 (isolates) and resource (the given pnt_ids in the open viewer) and even parenthetically defines what 'isolates' means (hides everything except). Distinguishable from the sibling viewer_isolate_models, which operates on models rather than pnt_ids.

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?

The description implies the tool is a viewer filter operation but gives no explicit when-to-use guidance, no prerequisite (a viewer must be open), and never names the alternative viewer_isolate_models. The distinction from that sibling is left to the reader.

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