wb_collisions

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

With no annotations, the description carries the full burden, and it does disclose a genuinely important behavioral trait: results are heuristic and marked approximate. It also reveals the underlying geometry method. What it omits is whether the scan mutates anything, how results are returned, and roughly how expensive it is on large builds.

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?

It is one front-loaded sentence with no filler, which is good, but it wastes half its length on redundancy ('Approximate ... marked approximate'). Brevity here reflects under-specification rather than disciplined editing.

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 four-parameter tool with no annotations and no output schema, the description should explain what the scan returns and what the parameters control. Instead it gives only a method note and an accuracy caveat, leaving the agent unable to invoke it confidently without guessing.

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 four parameters (file, catalog, clearance, explicit_only) exist, yet the description explains none of them. 'saved-build' loosely gestures at the file/catalog pair, but clearance tolerance and explicit_only semantics are entirely undocumented in both schema and description, which is a real gap for this tool.

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?

The description names a specific operation ('collision scan') on a specific resource ('saved-build') and adds a method qualifier ('yaw-aware oriented bounds'). However, it does not differentiate this from nearby siblings such as wb_validate or wb_compat_scan, so an agent cannot tell from the text alone which check it wants.

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?

There is no statement of when to run this versus alternatives, no prerequisites (does the build need to be saved/closed?), and no guidance on whether it is safe to run repeatedly. The word 'saved-build' weakly implies the target must be persisted, but nothing is explicit.

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