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

Annotations already declare the safety profile (readOnlyHint, destructiveHint=false), and the description adds non-annotation context: the OAuth project-read scope requirement and the non-destructive nature ('Loading does not modify the saved project') plus the return shape. The auth requirement is genuinely valuable behavioral disclosure.

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 sentences, front-loaded with the action and scope constraints, and no filler. Slightly more could be trimmed but it is efficient.

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 simple read tool with no output schema and rich annotations, it adequately covers the scope requirement, non-modification, and return form. However, the language parameter is left entirely unexplained, leaving a real gap an agent must guess at.

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 carry parameter meaning, yet it never explains projectId or the language enum (which appears to control localization). With two undocumented parameters, the description does not compensate for the coverage gap.

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 ('Retrieve') and resource ('one private VoxelDraft Cloud Project') and the output form ('compact MCP model handle'), which implicitly separates it from the plural list_voxel_projects. It is clear but never names a sibling to sharpen the contrast between loading versus listing or inspecting.

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?

It supplies one precondition (the project-read OAuth scope) and hints at why to load rather than fetch raw data ('preserving token efficiency'), but gives no explicit when-to-use/when-not guidance against siblings like inspect_voxel_model or list_voxel_projects. Usage must be inferred.

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