apply_modifier

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

The annotation already declares destructiveHint=true, and the description's 'destructively' simply restates that structured signal. The parenthetical 'bake' adds a little semantic color, but the description does not disclose additional behavioral consequences, such as whether the modifier is removed from the stack or whether the original geometry is overwritten.

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 description is a single focused sentence with no filler, and the parenthetical 'bake' efficiently clarifies the meaning of 'apply'. It front-loads the core action and the key consequence.

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 two-parameter tool with a destructiveHint annotation and no output schema, the description is minimally adequate: an agent can infer it must pass an object and modifier name to permanently apply the modifier. Still, it leaves open how modifier names are resolved and what happens after a successful apply, so it is not fully complete.

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?

With 0% schema description coverage, the description needed to compensate for parameter ambiguity, but it says nothing about object_name or modifier_name. The parameter names are self-explanatory at a basic level, so this is not a 1, but no extra meaning (name resolution, case sensitivity, multiplicity) is provided.

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 identifies a concrete action ('Apply', clarified as 'bake') and a clear resource ('a modifier'), and the word 'destructively' adds an important distinction from non-destructive modifier operations. It does not explicitly differentiate from sibling tools such as add_modifier or remove_modifier, so it misses the top score.

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?

The destructive/baking language implies the tool should be used when a modifier's effect is meant to be made permanent, which is useful context. However, it does not explicitly say when to choose this over sibling modifier tools or mention prerequisites such as the modifier already existing on the object.

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