select_faces

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

With no annotations, the description carries the full burden and does well: it declares the operation is non-mutating and enumerates exactly what is returned. It does not discuss limits or performance on large meshes, but the read-only semantics and output shape are disclosed.

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?

Front-loaded with the preview purpose, then a dense but well-organized enumeration of filter keys, ending with the mesh_info pointer. Every sentence earns its place, though the key listing is packed tightly.

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?

No output schema, but the description enumerates the return contents; no annotations, but read-only behavior is stated. For a two-parameter selection-preview tool, an agent has everything needed to invoke it correctly.

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 must compensate and it does thoroughly: it defines every `where` key (normal with angle, x/y/z ranges with null-as-open, box, area, index) plus the empty-object/null default. This is meaning far beyond the bare `additionalProperties: true` schema.

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?

Specific verb+resource ('Preview a face selection') with explicit scope ('without changing anything') and even names the returned quantities (count, area, world range, first indices). An agent can distinguish this from siblings like delete_faces or extrude_faces, which act on selections rather than previewing them.

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 a clear prerequisite ('Look at mesh_info first to see where the faces are') and states the default behavior ('{} or null picks everything'), which tells the agent when the filter can be omitted. It does not explicitly name an alternative tool for actually mutating the selection, but the preview-vs-act distinction is implied.

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