set_selection

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

With no annotations, the description carries the full burden of behavioral disclosure. It only states that objects are selected by name, but does not clarify whether this replaces the current selection, how 'extend' interacts, what happens when names are invalid, or whether the selection becomes active. This is a significant gap for a tool that clearly mutates 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?

The description is a single, terse sentence with zero redundancy. It front-loads the primary action and resource. While extremely short, it is not padded with fluff, making it highly efficient for scanning.

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 three parameters, an output schema, and no annotations, this description is seriously incomplete. It does not explain the semantics of 'active' and 'extend', the behavior on invalid names, or the structure of the response (even though an output schema exists, its content is not conveyed). An agent would likely need to inspect the schema or experiment to call this 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 0%, so the description must compensate. It implicitly documents object_names (the names to select) but says nothing about the 'active' or 'extend' parameters. Since the required parameter is at least hinted at, but the other two are entirely undocumented, the description adds only marginal value and fails to explain critical control flags.

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 verb 'Select' and the resource 'objects', and specifies the method 'by name'. It distinguishes this tool from get_selection (which retrieves the selection) and other selection-adjacent tools like frame_selected. However, it does not hint at the function of the 'active' or 'extend' parameters, which would sharpen the purpose further.

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 no guidance on when to use this tool versus alternatives like get_selection or other selection-manipulation commands. There is no mention of context, prerequisites, or exclusions. An agent must infer usage from the name and sibling list, which is not reliable for complex workflows.

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