select_faces_by_sides

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

With no annotations, the description carries the burden and does well: it discloses that selection is replaced by default, that `extend` adds instead, that the operation is scoped to a single mesh, and that a count is returned. It does not state mode requirements (object vs edit mode) or error behavior for non-mesh objects, which is the remaining gap.

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 purpose and the discriminating ngon/triangle use case, then structured Args/Returns. The restated enum values and the Returns block are mildly redundant given the schema, but nothing is confusing or padded.

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 mutation-style selection tool with no annotations, the description covers scope, side effects on existing selection, and return shape (an output schema also exists). The main missing piece is the execution context requirement — whether the mesh must be in edit mode or active — which matters for a selection tool.

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 coverage is 0%, so the description must compensate and largely does, explaining all four parameters including a domain constraint the schema lacks ("A face has at least 3") and the replace-vs-add semantics of `extend`. It doesn't mention the defaults baked into the schema (number=4, comparison=EQUAL), which would have helped an agent calling with only `object_name`.

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 plus a precise selection criterion: "Select faces of one mesh by how many sides they have." It also distinguishes itself from the crowd of selection siblings by naming the exact use case (ngons >4, triangles =3) and explicitly contrasts with select_objects for whole-object 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?

Gives explicit when-to-use guidance tied to a real workflow ("what topology cleanup usually needs") and an explicit when-not-to-use with the alternative named ("Works inside one mesh; to select whole objects use select_objects"). Nothing about tool choice is left to inference.

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