Mirror Elements

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds substantial context on top: exact skip categories and their output keys (skipped.inGroup, skipped.pinned, skipped.hosted, skipped.constrained), the guarantee those elements are unchanged, the all-group-members refusal condition, and dry_run rollback. This is precisely the behavioral disclosure a destructive tool needs.

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?

The core operation and axis constraint are front-loaded in the first clause, and the remaining sentences are dense with non-redundant specifics about skipping, refusal, and rollback. It is terse and slightly run-on but every sentence carries operational weight.

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, non-idempotent mutation with an output schema, the description covers the critical unknowns: what is left untouched, when the call fails outright, and how dry_run behaves. Only minor gaps remain, such as document-scoping requirements and whether the operation applies model-wide versus to the active view.

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 only 17% (only document is documented in the schema), so the description carries the burden and does so for most parameters: axis is constrained to x/y, point_mm is the point the mirror line passes through, copy retains originals, and dry_run rolls back. element_ids and document semantics are left to the schema, which mildly undersells the required element list.

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 description names a specific verb (mirror), the resource (elements), and the precise geometric constraint (a model X or Y parallel line through point_mm), which immediately distinguishes it from sibling mutations like revit_move, revit_rotate, and revit_copy. An agent can identify the operation without opening the schema.

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 implies usage through mode semantics – dry_run rolls back and copy keeps originals – so an agent can infer a safe-preview path versus a mutating path. However, it never states when to reach for revit_mirror rather than revit_copy or revit_rotate, and gives no prerequisites for when a document must be specified.

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