workspace_state

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

No annotations are provided, so the description carries the full burden. It discloses significant side effects: 'changes (recent added/removed instances — installs a watcher on first call)' and 'clear_cache (drop watchers and cached plugin state)'. These reveal non-obvious behaviors beyond the schema. It also clarifies the destructive nature of clear_history and clear_cache. The description could have been more explicit about read-only safety for other actions, but it does highlight the main side-effectful operations.

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 description is a dense single paragraph with a two-word opening and a semicolon-separated action list. It is concise given the number of actions (11), and each action's description is brief and informative. It is not bulleted, but the structure is readable and each word contributes. It could be improved by using a list format, but it remains appropriately sized for the tool's complexity.

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?

With 11 actions, 8 parameters, no annotations, and no output schema, the description covers all actions with understandable summaries and highlights key side effects and parameter usage. It does not provide detailed return value formats, but given the absence of an output schema, this is acceptable. It also does not explicitly describe what 'summary' includes beyond 'place info, top-level services, selection, camera', or the behavior of 'topN', but overall it is sufficiently complete for an agent to select the right action.

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 description adds meaning beyond the schema by mapping parameters to actions: 'counts (instance counts by ClassName under a path)' clarifies the path parameter, and 'snapshot (instance tree under a path, maxDepth)' links path and maxDepth. It also clarifies that includeMetadata relates to sync. However, the topN parameter is not described anywhere, and the schema already provides descriptions for limit, maxDepth, includeMetadata, includeCameraInfo, and includeSelectionBounds. The description adds value for path and action-parameter associations but leaves a gap.

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 clearly defines the tool as a 'Snapshot of the place' and then enumerates eleven specific actions, each with a concise description of what it returns (e.g., 'counts (instance counts by ClassName under a path)', 'viewport (camera + viewport size + selection bounds)'). This provides specific verb-action-resource tuples and distinguishes it from sibling management/query tools by focusing on state introspection rather than mutation.

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?

Each action is described with its exact use case (e.g., 'sync (hierarchy outline + metadata + change stats)', 'scripts (all script paths with line counts)'), giving clear context for when to use a particular action. However, the description does not explicitly mention when to prefer this tool over sibling alternatives like query_instances or spatial_query, nor does it state exclusions. The guidance is implied by the action list.

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