find_floating

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

With no annotations, the description carries the full burden and largely meets it: it explains grouping logic, how the main group is chosen, that results are folded to max_listed with a count, and the fallback defaults for empty touch/search/near. It does not explicitly state that the tool is read-only/non-mutating, which is the one behavioral trait left to inference.

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?

Front-loaded with the core definition before the defaults and follow-up advice, and every sentence carries information. It is dense and some sentences pack multiple clauses (e.g. the size-scaling examples), which costs a bit of readability but no sentence is filler.

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?

There is no output schema, so the description explains the return shape (nearest part and gap per floating group, tiny_gaps pairs, folding with a count), which is appropriate. It is nearly complete for a six-param tool; the only omission is any explanation of the `names` filter parameter.

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 0%, so the description must compensate, and it does for five of six parameters: near (2% of the pair diagonal, capped at 0.03 m), touch (0.001 m scaled by part size), search (1 m scaled), ground_z, and max_listed. The `names` parameter is never mentioned, leaving one gap in an otherwise strong compensation.

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 ('Find parts that hang in the air') and immediately defines the concept operationally: meshes that touch/overlap form groups, the group standing on ground_z (or largest) is the main one, everything else is floating. An agent can distinguish it from siblings like check_contacts, ground, or move_to_contact without opening the schema.

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?

Gives explicit timing and follow-up ('Run it after assembling a model, then fix with move_to_contact or attach'), naming the concrete remediation siblings. It lacks an explicit when-not-to-use or a contrast against check_contacts, 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.