list_edges

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

With no annotations, the description carries the full burden, and it delivers key behavioral context: what each returned edge includes, that lines additionally carry axis and midpoint, and critically that indices are always whole-part indices (stable regardless of filtering). It doesn't state read-only safety or error behavior, but the disclosed index semantics are a genuine behavioral trait beyond the schema.

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-loads the purpose and return shape, then the filters, then the index-usage note, with no filler sentences. The line break lands mid-clause ('face (a list_faces index, "#5")') and the density is high, but every sentence earns its place.

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?

With no output schema and no annotations, the description still covers the return fields, all filter parameters, and how the indices are consumed downstream, which is enough to invoke the tool correctly. It omits pagination/limits and error behavior on an invalid face/feature, minor gaps for a listing tool.

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 fully, and it does: face is given the '#5' format and its source (a list_faces index), feature is defined as the edges of the faces it made, within_mm is given the explicit [[x1,y1,z1],[x2,y2,z2]] shape and 'both ends inside' semantics, and min_length_mm is self-describing. This is far richer than the empty schema.

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 ('List the part's edges') and immediately enumerates the returned fields (index, type, length, ends, axis, midpoint), which distinguishes it from sibling listing tools like list_faces and list_bodies. An agent can tell exactly what this tool produces 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?

Explicitly tells the agent to 'Narrow it on a big part' and lists the filter conditions for doing so, plus how the returned indices feed into add_fillet/add_chamfer. It lacks an explicit statement of when NOT to use it or a named sibling alternative, so it falls just short of a 5.

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