scatter

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

Annotations only declare readOnly=false/destructive=false/openWorld=false, which is consistent with adding objects to a scene. The description adds substantial unsurfaced behavior: seed determinism ('The same seed gives the same result'), a performance tradeoff ('linked=true shares one mesh (cheap)'), and the nature of the returned result (counts per source and rejection reasons too_close/not_on_surface/too_steep).

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?

Purpose is front-loaded and sentences are densely informative with almost no filler, which is justified for 13 undocumented parameters. It is delivered as a single unstructured paragraph, so parameter groups are harder to scan than they could be.

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?

No output schema exists, yet the description explains the return value (per-source counts plus rejection reasons), covers determinism, memory cost, and the sibling alternative. For a complex 13-parameter mutation tool, an agent has everything needed to call it correctly.

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% across 13 params, so the description carries the full burden and mostly succeeds: it defines `source` list semantics, `weights` odds, `area` as [x0,y0,x1,y1] with a default, plus min_distance, max_slope_deg, align_to_normal, scale_range [min,max], yaw_random, seed, and linked. Gaps remain for `name` and the format of `surface`.

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 ('Place') plus resource ('`count` copies of an object at random on top of surface objects') with examples of what gets scattered (trees, rocks, crates, grass). It explicitly distinguishes itself from the sibling `place_on` by naming that tool for the single-placement case.

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 routes the agent to the alternative explicitly: 'For one object at a chosen spot use place_on.' That is a clear selection condition. It lacks broader when-to-use framing (e.g., scene-population intent) or when-not-to-use, but the sibling handoff is unambiguous.

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