blender_mesh_extrude

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state a key behavioral trait — "creates new geometry by extending existing elements outward" — which correctly signals a topology-mutating operation. However, it fails to disclose consequences such as the original elements being moved/replaced, the operation being destructive except via undo, or failure modes when indices don't match the selected mode. The core mechanic is clear, but side effects and risks are left unstated.

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 tight sentences with the verb and resource front-loaded in the first sentence. The second sentence earns its place by framing the operation's nature (creating geometry by extension), though "most fundamental" is mildly promotional. No redundancy with the schema; every clause carries some signal.

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 mid-complexity tool (5 params, enum, arrays, 3 required) with no output schema and no annotations, the description is functional but thin. It explains what the operation does, and the schema fills in parameters, but an agent is left without knowledge of return behavior, prerequisites, or how this operation relates to its siblings. Adequate for a basic call; incomplete for confident autonomous selection in a 150-tool environment.

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 description coverage is 100%, so the schema already documents all five parameters adequately, which sets the baseline at 3. The description adds minimal parameter insight beyond reinforcing the offset vector concept in its prose. The relationship between mode=REGION and the 'individual' flag is slightly underspecified even in the schema, but the description neither worsens nor meaningfully improves parameter understanding.

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 first sentence uses a specific verb and resource: "Extrude faces, edges, or vertices along an offset vector," which precisely identifies the operation and its target. The second clause, "creates new geometry by extending existing elements outward," conceptually distinguishes extrude from modifying operations like bevel, inset, or dissolve, though it never names a sibling explicitly. In a suite of ~150 tools it could differentiate harder, but the core purpose is unmistakable.

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?

No guidance is given on when to use extrude versus the many sibling mesh operations (bevel, inset, loop_cut, bridge, array_along_curve), and no preconditions are stated (e.g., object must exist, indices must be valid for the mode). The phrase "most fundamental mesh modeling operation" only implies general applicability and does not help an agent select between alternatives. This is a clear gap for a tool in such a large family.

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