Modify curtain walls

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, but the description adds real behavior: changes happen in a single undo step, the return shape is [{guid} | {error}], and the base-line immutability is disclosed. This is more than the annotations convey and useful for planning a mutation.

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 verb, then the constraint, then the return shape. The middle sentence is dense but every clause enumerates a distinct modifiable facet, so little is wasted; only the very long single sentence risks being hard to scan.

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 destructive multi-field mutation with full annotation coverage, the description supplies the missing pieces: undo semantics, return format, and the immovable base line. No output schema exists, yet the description states the return shape, so an agent has enough to call it correctly.

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 baseline is 3; the description goes further by explaining that primaryGrid/secondaryGrid are module widths/heights, that the *Spacing fields are shorthands for FixedSizes grids, and that surface/material fields apply to ALL panel and frame classes. That clarifies scope of each patch field beyond the schema text.

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 (changes) and resource (existing curtain walls), and enumerates the exact modifiable facets: height, flip, grid patterns, surfaces/thickness, frame materials, zone relation, floor plan display. It also names the sibling tools that must be used instead for the base line (move_elements/rotate_elements or recreate), so it can be told apart from modify_curtain_wall_parts and the transform tools.

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?

Explicitly states the boundary condition: the base line cannot be changed and directs the agent to move_elements/rotate_elements or recreation. It does not, however, distinguish itself from the sibling modify_curtain_wall_parts, which is the most likely nearby alternative, so the guidance 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.