manage_selection

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

No annotations are provided, so the description carries the full behavioral burden. It discloses non-obvious behaviors such as 'cached' avoiding a Studio round-trip and 'watch' requiring a second call to collect changes. It also hints at return structure (details, context). While it does not explicitly mention side effects of mutation actions, the action names (add/remove/clear/set) clearly imply selection modification, and the description adds meaningful context beyond the schema.

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 front-loaded with the core purpose and then lists actions with parenthetical parameter and behavior notes. It is concise and avoids redundancy, though the single-sentence structure is dense and could be improved with a bulleted list. Still, every word earns its place.

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 tool with 9 actions and 8 parameters, the description covers all action variants and their parameter dependencies, including return semantics for details, cached, and context. It lacks explicit error handling or prerequisites, but given the complexity and absence of an output schema, it provides sufficient context for an agent to select and invoke the tool correctly.

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 75%, with descriptions for maxAge, maxDepth, includeSource, includeChildren, includeAncestors, and includeProperties. The description adds meaning for the undocumented parameters: 'paths' is explicitly tied to the 'set' action, and 'action' is fully explained by the enumerated action list. It also associates each parameter with its relevant action, enhancing understanding beyond the schema.

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 states the tool's purpose: 'Get or set the Studio selection.' It enumerates all supported actions (get, set, add, remove, clear, details, cached, context, watch), specifying the resource (selection) and distinguishing it from sibling instance management tools like query_instances or mutate_instances.

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 provides brief context for each action (e.g., 'cached' for last known selection without round-trip, 'watch' for installing a watcher), which helps the agent choose the right action. It does not explicitly contrast with sibling tools or mention when not to use this tool, but the selection-specific scope makes it the obvious choice for selection operations.

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