shrinkwrap

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds context beyond that: it specifies that vertices are moved (what gets modified), how offset creates a gap in metres, and the subdivide-first workflow prerequisite.

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 dense sentences front-load the core action before drilling into method, offset, and the prerequisite. Every sentence carries information, though the parameter detail could be organized more cleanly.

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 6-parameter destructive tool with no schema descriptions and no output schema, the description leaves meaningful gaps: two of three method enum values are unexplained and the object/target inputs are only implied. It is adequate but not complete enough to call the tool correctly without opening the schema.

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 must carry the full parameter burden and only partly does. It explains `axis`, `direction`, and `offset` (metres) but only describes the `project` method, leaving `nearest_surface` (the actual default) and `nearest_vertex` undefined; it also claims `axis` defaults to Z while the schema default is null.

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 relationship ('Snap the vertices of `object` onto the surface of `target`') rather than a vague action. The vertex-level framing plus concrete examples (clothes onto a body, a clean mesh onto a sculpt) distinguish it from placement siblings like place_on or move_to_contact.

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 parenthetical examples give clear use-case context for when this tool applies, and 'Subdivide the object first for a smooth fit' is a useful prerequisite. It never names or excludes alternatives such as place_on or ground, so the routing guidance stops short of a 5.

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