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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds real value beyond them: the silent-degradation failure mode (a non-watertight mesh is dropped from a boolean with no error), and dryRun as a non-mutating preview. It does not state whether a repair is reversible or how partial failures are reported, leaving a modest 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?

Three sentences, front-loaded with the action and followed by the rationale and the dry-run escape hatch; nothing is redundant. The boolean-failure explanation is slightly long but it earns its place by justifying the tool's existence.

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 destructive, no-output-schema tool this covers purpose, trigger, risk, and safe preview well, and annotations carry the safety profile. The one omission is what a successful repair returns or reports, which the agent must infer.

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 100%, so projectId, nodeId, version and dryRun are all documented in the schema, including the subtle version-required-only-on-write rule. The description only restates dryRun's behavior, adding no syntax or format detail beyond the schema — baseline 3 is correct.

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 — finding non-watertight imported meshes and welding cracks, closing holes, fixing face directions — which is far more precise than the title alone. It is clearly distinguishable from siblings like edit_nodes, evaluate, or print_check because it names the exact defect class it targets.

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?

"Run this when a project contains an import and the geometry is not behaving" gives a clear triggering condition, and the dryRun sentence supplies a safe-preview path. It stops short of naming an alternative tool or an explicit when-not-to-use case, so it falls just short of the top band.

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