add_viewmodel

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

Annotations already declare readOnly=false, destructive=false, openWorld=false, so safety is covered; the description adds the non-obvious return shape (already_existed, view_model_count, has_mvvm_extension), which is real behavioral value given no output schema. However it omits failure modes such as the PIE-session refusal and the on-disk save implication, so it is only partially transparent. There is also mild tension with idempotentHint=false, since an "already_existed" return implies repeat-call stability.

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?

Two sentences: the mutation is front-loaded, followed by a compact return declaration. Nothing is wasted, and the return list compensates for the absent output schema rather than padding.

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 7-parameter mutation on an asset's authoring state, the description covers what and returns but not when to prefer it, what happens on collision with an existing context, or any prerequisite/preconditions. It is adequate but leaves the selection and precondition gaps to the schema and annotations.

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% and the schema documents every parameter in depth, including the enum-like creation_type values and the conditional requirements for source_property_path/global_identifier. The description adds nothing beyond that, so the baseline of 3 applies.

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: "Append a UMVVMViewModelContext" to a Widget Blueprint's MVVM authoring state. The scope is unambiguous, but the description never distinguishes this from the closely related siblings remove_viewmodel, set_viewmodel_field, or bind_widget_to_viewmodel, so an agent must infer which one applies.

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?

No when-to-use, when-not-to-use, or alternatives are stated. The only conditional guidance (the PIE refusal and force flag) lives in the schema for the force parameter, not in the description. An agent gets no routing help toward remove_viewmodel or the binding tools.

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