Group elements

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

Annotations only declare the generic mutation profile (readOnly false, idempotent false, destructive false); the description carries the real behavioral load. It discloses the non-obvious nesting semantics ('elements that already belong to a group bring their whole top-level group, which becomes a nested sub-group'), the story constraint, and that the `groups` form batches multiple creations into a single undo step — all of which explain the non-idempotent hint and go well beyond the annotations.

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 core action and then layered with the highest-value details (nesting, story constraint, mode selection, return shape) in a compact run of sentences. It is dense rather than padded, though the trailing sentence listing return shapes and follow-up tools is slightly list-heavy.

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?

There is no output schema, yet the description supplies the return shape ({groupGuid, members, elementCount}, and {results:[...]} for the `groups` form), the preconditions, and the nesting behavior. For a non-idempotent mutation with 3 parameters, nothing an agent needs to invoke it correctly appears to be missing.

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 100%, so the baseline is 3, but the description adds semantics the schema cannot express: `elements` versus `groups` are alternative entry points, the latter nests the same shape plus an optional parentGroup, and the union selects single-group versus bulk behavior. The story precondition is reinforced for both paths. It adds real value but does not spell out per-parameter format constraints (e.g., GUID formats) that live in the schema.

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 ('Groups elements') and even maps it to the Archicad UI path (Edit > Grouping > Group), immediately distinguishing it from siblings like ungroup_elements and merge_elements. The scope (elements move/select together, same story) is concrete enough that no schema reading is required.

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 explains the two invocation modes ('Pass elements for one group, or groups: [{elements, parentGroup?}] for several in one undo step') and states a hard precondition ('All elements must be on the same story'). It also routes the agent forward by noting the returned GUID can feed move_elements/delete_elements/ungroup_elements. It does not, however, contrast against a genuine alternative such as merge_elements, so it stops short of full when/when-not guidance.

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