construct_object

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

The description goes beyond the raw annotations by detailing the multi-step workflow: analysis, sampling request to an LLM, code generation, validation, execution, and iteration. It highlights 'Security and syntax validation' and 'Safe execution in Blender with error handling.' Since annotations already indicate the tool is not read-only and not idempotent, the description adds useful context about the LLM involvement and safety measures, though it does not explicitly warn that the tool may modify existing scene objects.

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 quite verbose and front-loaded with a 'PORTMANTEAU PATTERN RATIONALE' section that discusses design rationale and FastMCP best practices, which is not directly actionable for an agent selecting the tool. While the sections are well-organized and the content is relevant, several sentences could be trimmed to improve brevity without losing essential guidance.

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 complex tool with 8 parameters and an output schema, the description covers a lot: the agentic workflow, supported complexity levels, style presets, and iteration behavior. It lacks some operational prerequisites (e.g., Blender must be running) and explicit alternatives, but given the rich schema and annotations, the description is largely complete for an agent to understand scope and capabilities.

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 input schema provides 100% coverage, but the description adds meaningful semantic depth by explaining the complexity levels ('simple', 'standard', 'complex') with concrete examples and the style presets ('realistic', 'stylized', 'lowpoly', 'scifi'). This helps agents choose appropriate parameter values beyond the schema's minimal descriptions. The workflow section also clarifies how max_iterations fits into the process.

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 that this tool performs 'Universal 3D object construction using natural language and LLM-generated Blender scripts.' It uses a specific verb ('construction') and resource ('3D object'), and distinguishes itself by positioning as the consolidated natural-language interface, preventing tool explosion. This differentiates it from siblings like generate_blender_script or script_execute by emphasizing its agentic, LLM-driven approach.

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 clear context on when to use the tool: for natural language 3D construction across varying complexity levels and with style presets. It explains the agentic workflow and supported complexity levels, which implies usage scenarios. However, it does not explicitly state when not to use it or mention alternative tools (e.g., 'for direct script execution use script_execute'), leaving exclusion guidance implied rather than explicit.

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