select_faces

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the description doesn't need to establish the safety profile. It goes beyond that by specifying the exact return shape (count, area, world range, first indices) and the default angle (25°), which is meaningful behavioral detail. It doesn't discuss pagination or size limits on large selections, keeping it from 5.

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 key preview behavior and return fields are front-loaded in the first sentence, and the `where` grammar follows. It's dense but every clause carries parameter meaning. Slightly prose-heavy for a tool description but no filler.

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 2-parameter read-only tool with no output schema and 0% schema coverage, the description covers the selection grammar thoroughly and names the preview output. It leaves minor gaps (no mention of performance on large meshes, no reference to sibling selection-based operations), but is largely 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?

Schema description coverage is 0%, so the description carries the full burden for `where`, and it delivers: it enumerates every supported key (normal with angle default 25°, x/y/z ranges with null-open semantics, box, area, index) and states the AND-semantics ('all given keys must hold') plus the empty-object/null default. This is exactly the compensation needed at 0% coverage.

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 opens with a specific verb+resource and scope: 'Preview a face selection without changing anything'. It also enumerates exactly what is returned (count, area, world range of centres, first indices), which distinguishes it sharply from siblings like `delete_faces` or `extrude_faces` that actually mutate the selection.

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?

Usage context is clear ('Preview...without changing anything', 'Look at mesh_info first to see where the faces are'), and the read-only intent implies this is used before mutating operations. It doesn't explicitly name the mutating alternatives (extrude_faces, delete_faces, inset_faces, etc.) it's meant to precede, so 4 rather than 5.

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