Thickness

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

Annotations indicate readOnlyHint=false and destructiveHint=false, but the description does not add meaningful behavioral context beyond the parameter explanations. It does not disclose side effects (e.g., whether the original body is replaced), requirement for a 'tip feature', or any constraints on the solid shape. Since annotations are minimal (false flags do not describe the nature of the mutation), the description carries the burden but fails to elaborate on behavior beyond the immediate hollow-out action.

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 description is compact and front-loaded with the core purpose. The parameter list is structured efficiently, each line providing specific value. No unnecessary words, though the formatting is a plain list rather than a structured breakdown. It earns high marks for concision and clear organization.

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 tool with 7 parameters, no output schema, and no enum constraints, the description covers parameter semantics well but misses contextual details: it does not mention the requirement for a solid body, the meaning of 'tip feature', or the result of the operation (e.g., a modified body object). It also does not reference the similar shell_solid tool, leaving ambiguity about when to use this instead. Given the complexity and the existence of a likely-sibling tool, more context is needed.

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. It explains each parameter: base as the handle of the tip feature, open_faces as openings, thickness as wall thickness with units, reversed with directional meaning, and join/mode with enumerated options. This goes well beyond the bare schema, giving the agent full understanding of parameter intent and defaults.

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 'Hollow out a solid into a shell,' which clearly defines the operation and its object. It specifies the resource as a solid and the action as hollowing, making the purpose unambiguous. However, it does not differentiate from the sibling tool 'shell_solid', which likely performs a similar function, so it lacks explicit sibling differentiation.

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?

The description provides no guidance on when to use this tool versus alternatives like shell_solid or other shelling approaches. It does not state prerequisites, conditions, or exclusions. The only contextual hint is the tool name and title, which are not sufficient for an agent to decide between this and a sibling.

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