evaluate_expression

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

The readOnlyHint annotation already declares the safety profile, and the description reinforces it with 'Safe for read-only queries'. It adds the context that it executes inside Blender and returns a result, but offers no detail on error handling, restrictions, or side effects beyond what the annotation already implies. No contradiction with annotations.

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?

Two short sentences with the core purpose in the first sentence and clarifying examples in the second. Every word earns its place; no filler or redundancy.

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 single-parameter, read-only evaluation tool with an output schema, the description is sufficiently complete. It covers what the tool does, gives usage examples, and reinforces the safety annotation. It could mention error handling or that the expression must be a single Python expression, but the output schema and simple interface lower the burden.

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 schema's only parameter 'expression' has no description (0% coverage), so the description must explain its semantics. It does so by defining it as a Python expression and providing two concrete examples. This gives the agent actionable understanding of what constitutes a valid expression, though it doesn't fully explore edge cases like multi-statement or non-read-only usage.

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 uses the specific verb 'Evaluate' with a clear resource ('a Python expression inside Blender') and states the return behavior ('return the result'). It also provides concrete examples ('len(bpy.data.objects)', 'bpy.context.mode') that clarify the scope and distinguish it from the more general execute_python sibling by emphasizing read-only queries.

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 phrase 'Safe for read-only queries' gives clear context for when to use the tool, and the examples illustrate suitable use cases. However, it does not explicitly name alternatives (e.g., execute_python) or state when not to use it, so it's not a full 5.

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