Modify elements

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

Well beyond the annotations: it discloses the dry-run default and its per-element current/new value return shape, the exact skip conditions (other view, hidden/locked layer, unreserved in Teamwork, hotlinked module) and that it never unlocks anything, and what a commit reports ('modified', 'failed', 'not_applied'). The destructiveHint is thereby given operational meaning rather than just echoed.

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?

Dense but every clause earns its place, and the single most decision-critical fact (dry-run by default) is front-loaded in the first sentence. The long sentence about which element types take Modify<Type> fields is information-bearing rather than filler.

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 very high-complexity mutation tool with an arbitrary-object parameter, the description covers field naming, units, skip semantics and post-commit verification; the output schema existing means the return-shape explanation is a bonus rather than a requirement. Only the port parameter and the GUID-discovery path (how to obtain guids, presumably via find_elements) are left unaddressed.

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% and the changes array is an untyped object bag, so the description carries the full burden — and it does, spelling out the {"guid", ...fields} item shape, the per-element field vocabulary, units (metres/radians/mm), and partial-value completion from current values. The port parameter is never mentioned in either place, which is the remaining gap.

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 ("Change existing elements") and enumerates the element families and field families it accepts, so the scope is concrete. It never names a sibling (set_element_data, move_elements, set_selection) to say where its boundary lies, so differentiation is left to inference.

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?

It clearly conveys the default mode (dry-run) and the condition to commit ("pass dry_run=false to commit"), which is real usage guidance for one parameter. There is no guidance on when to pick this over set_element_data or move_elements, nor any exclusion-by-alternative, so usage is implied rather than stated.

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