solid_transform

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

Annotations only declare readOnlyHint=false; the description adds the concrete side-effect (modifies solid position/orientation) and the input-rejection rule, going beyond the annotation. It omits whether changes are undoable/transactional and how non-solid handles are rejected, which would fully close the loop for a mutation tool.

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?

Three tight segments — capability, side-effects, disambiguation — with the constraint (no free-form matrices) placed up front. No filler sentences.

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?

Output schema exists, so return values needn't be described, and the mutation side-effect is disclosed. Slightly incomplete for a write tool on nested 'parameters' — it doesn't say what happens on a malformed operation/parameter combination or whether a transaction context is required.

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 baseline is 3, but the description contributes real meaning beyond the schema: it constrains 'scale' to uniform scaling and frames 'operation' as a closed typed set, neither of which the schema states explicitly. It doesn't add per-operation parameter validity rules (e.g. required plane for mirror).

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 (apply) plus the exact set of accepted operations (move, rotate, uniform-scale, mirror) on a specific resource (ACIS solid). The disambiguation line scopes it as 3D spatial transformation for ACIS bodies, distinguishing it from the generic object_move/object_rotate/object_scale and batch_transform_entities siblings.

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?

Gives an explicit exclusion — free-form matrices and arbitrary commands are rejected — which tells the agent when not to reach for this tool. It stops short of naming the alternative (object_move, object_rotate, batch_transform_entities) for non-ACIS or batch cases, leaving that inference to the agent.

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