add_driver

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

With no annotations, the description does substantial work: it discloses that expressions are evaluated without Python, enumerates the exact supported grammar and the operators that will fail (no **, use pow), and caps variables at 32. What it omits is mutation semantics — whether an existing driver on the same data_path is replaced or errors, and whether the operation is reversible.

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 purpose and examples, then cleanly structured into an expression-grammar block, an Args block, and a Returns block. Dense but nearly every clause carries information; the three opening vignettes are illustrative rather than strictly necessary, which is the only padding.

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?

An output schema exists, and the description still summarizes the return dict, so return values are well covered. All six parameters are documented for a tool with 0% schema coverage. The remaining gap is the absence of any note about pre-existing drivers on the same path or failure modes, which matters for a mutation tool with no annotations.

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 0%, so the description carries the full burden and does so thoroughly: every parameter is explained, data_path gets four concrete path examples including nested shape-key and modifier paths, index is explained as vector-component vs -1 sentinel, and the variables structure is broken out by variable type (TRANSFORMS with transform_type/transform_space defaults, SINGLE_PROP, LOC_DIFF/ROTATION_DIFF with object_2).

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 ("Drive a property from other properties or the frame") and immediately grounds it in three concrete scenarios (door/handle, wheel/car, light/distance). This is clearly distinguishable from the sibling driver tools (list_drivers, remove_driver) and from keyframe_property, since the mechanism is property-to-property linkage rather than time-based keys.

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 opening examples give clear context for when a driver is the right mechanism, and the driver_type parameter is explained as a branching choice (SCRIPTED vs AVERAGE/SUM/MIN/MAX). However, it never explicitly says when not to use this tool or names the alternative (e.g. insert_keyframe for time-based animation, or list_drivers to check for an existing driver first).

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