geometry_face_set

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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the mutation profile is known. The description still adds real value beyond that by disclosing atomicity, undoability, and that degenerate zero-volume results are rejected — but it says nothing about preconditions such as revision/epoch matching that a destructive edit would need.

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 tightly packed sentences with no filler, and the core action is front-loaded. The telegraphic notation ('order (R,C)=00,10,01,11') is compact but sacrifices readability, which costs it a point.

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 five-parameter, zero-coverage, destructive geometry mutation with no output schema, the description covers the geometric semantics well but leaves the epoch/revision/request_id contract and any return/confirmation behavior undocumented. An agent could call it, but not confidently reason about stale-map or retry behavior.

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 carries the full burden and mostly meets it: it defines depth units (0..8 in grid/8 units), the four-value ordering via (R,C)=00,10,01,11, and the per-axis pairing rule (X uses Y/Z, etc.), and identifies face with selection.orient. The concurrency parameters (request_id, map_epoch, expected_revision) remain entirely unexplained, keeping it below 5.

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: 'Set four absolute face-axis depths... on each exact nonempty leaf', which is concrete enough to distinguish a face-depth edit from sibling operations like geometry_vertex_set or geometry_fill. It stops short of naming an alternative, but the operation itself is unambiguous.

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?

There is no when-to-use / when-not-to-use guidance and no routing to alternatives such as geometry_fill or geometry_vertex_set. The only conditional language ('each exact nonempty leaf', 'invalid/zero-volume shapes rejected') describes validation outcomes, not selection guidance for the agent.

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