select_by_index

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

With no annotations, the description carries the full burden, and it delivers real behavioral context: deterministic with no operator or viewport dependency, selection replacement vs. addition via 'extend', and input validation constraints ('must be non-negative and within the mesh'). It omits context requirements an agent could stumble on — e.g. whether the object must be active/selected or what mode Blender must be in — and does not say what error surfaces on an out-of-range index.

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?

Front-loaded with the core action, then the differentiator, then arguments — the structure an agent scans well. The 'no operator, no viewport, no guessing' flourish is slightly editorial, and the Returns block partly duplicates the output schema that already exists, but neither is costly.

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?

Return shape need not be explained given an output schema exists, and argument meaning is covered. What keeps this from full marks is the missing invocation context: mesh-editing tools like this typically depend on object/mode state, and nothing in the description or (absent) annotations tells the agent how to prepare the scene before calling.

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, and it largely does: it documents all four parameters in an Args block, adding meaning the schema lacks — the non-negative/in-range constraint on 'indices' and the add-vs-replace semantics of 'extend'. Minor waste in restating 'element' as VERTEX/EDGE/FACE, which the enum already conveys, and 'object_name' is left purely tautological.

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?

States a specific verb and resource ('select specific vertices, edges or faces ... by index') and delimits scope ('of one mesh'), so an agent immediately knows this is index-driven sub-object selection rather than object-level or heuristic selection. It explicitly names the sibling it is not ('To select whole objects in the scene, use select_objects'), which disambiguates it within a very crowded select_* family.

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?

Gives a concrete when-to-use chain: analyze_mesh_quality emits defect indices, and this tool is how to act on them. It also names one alternative (select_objects) with its scope. It does not address the other selection strategies in the sibling list (select_similar, select_by_axis, select_faces_by_sides, select_all_geometry), so the routing is clear but not exhaustive.

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