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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds a backend dependency ('requires the MCP face-metadata endpoint in the configured backend') and an interpretation caveat about tessellation vs. intended draping surface, which is meaningful behavior beyond the structured fields.

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 short, front-loaded sentences with no filler; the primary capability leads and the caveats follow. Slightly verbose line-wrapping but every sentence adds information.

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?

An output schema exists, so return values need not be explained, and the annotations cover safety. However, the four parameters are invisible in both description and schema, so an agent cannot tell how to page or what the required IDs must look like — a real gap for a list tool with pagination.

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% for all four parameters, so the description carries the full burden and explains none of them. It says nothing about workspace_id/step_id formats or the limit/offset pagination controls (defaults 50, max 100), leaving required inputs and paging behavior undocumented.

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 (Inspect) and resource (STEP face IDs) and enumerates the returned attributes (areas, bounds, centroids, neighbours, mesh normals). It is clearly a read/inspect tool distinct from siblings like select_faces or mesh_landmarks, though it never names those siblings to sharpen the boundary.

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 real context: it requires the MCP face-metadata endpoint, warns that centroids/bounds describe the tessellation rather than a guaranteed intended surface, and tells the agent to ask for explicit face IDs when the surface cannot be identified here. That implies the select_faces handoff without naming it as an alternative, so it stops short of explicit when-not guidance.

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