elements_remove_overlaps

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

The description goes beyond the lone destructiveHint annotation by disclosing mechanism (deterministic translation, one axis, Inkscape visual bounds) and the crucial guarantee that path geometry is untouched — i.e. only positions change. It omits revision/concurrency behavior and permission context, but the core mutation semantics are clearly explained.

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?

Two tightly written sentences, no filler. The positive behavior is front-loaded and the exclusion clause follows immediately, which is exactly the right ordering for this tool.

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 no coverage, and the geometry-preservation guarantee is valuable. However, for a destructive positional mutation requiring expectedRevision and workspaceId, the description says nothing about the optimistic-concurrency contract or what a failed call looks like, leaving a material gap.

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% and none of the six property descriptions add meaning: 'axis' is only echoed as 'one axis', and gap, ids, path, workspaceId and expectedRevision are never explained. With five undocumented parameters including a revision token and ID list, the description fails to 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 and resource ('Separates overlapping SVG elements') plus the mechanism (deterministic translation on one axis using Inkscape visual bounds), which is enough to distinguish it from paths_boolean, elements_delete and path_modify. It does not, however, differentiate itself from close siblings like elements_arrange, elements_align or elements_distribute.

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 negative clause ('does not union, trim, delete, or otherwise alter path geometry') tells the agent when NOT to reach for this tool versus boolean/path-editing siblings. There is no positive guidance on when to choose it over elements_align, elements_distribute or elements_arrange, so usage is only implied.

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