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

With no annotations, the description carries the full load and does well: it states the preservation guarantee ('untouched zones keep their exact transforms'), two hard limitations, and the billing model ('$0.50 USDC via x402, charged only on success'). It does not cover whether a revision supersedes the prior placement or what the response contains.

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 tight sentences with the primary action front-loaded, followed by the exclusion and then the price. Every sentence adds information; the closing 'Part of Level design: Level dressing for 3D games' is the only near-filler, though it does supply category context.

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?

The schema is large and deeply nested (50 edits x 12 rules across six union variants) with 0% description coverage, no annotations, and no output schema. The description explains behavior and pricing but leaves an agent without any guidance on constructing edits or what jobId refers to, which is a substantial gap for a tool this complex.

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, and it does not. The three parameters (jobId, edits, instruction) are never explained, and the six rule kinds (scatter, cluster, along, ring, lot, anchor) go unmentioned. Phrases like 'denser or sparser, other assets, remove a kind of prop' gesture at rule semantics but do not map to any parameter.

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?

Specific verb ('Change') plus resource ('a placed level') and the two supported modes (free-form instruction or structured zone edits). It also distinguishes itself from the 2D sibling by framing itself as 'Level dressing for 3D games' and from a fresh placement by operating on an already-placed level.

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 explicitly names a failure case and the alternative workflow ('cannot cut an empty area inside a zone or move one object: for that, add a keep-clear zone to the layout and place again'). That routes the agent to level_design_place when the request falls outside scope. It stops short of explicitly contrasting with level_design_place for initial placement or with level_design_revise_2d.

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