list_edges

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 warns that ids are only stable relative to '1 = the longest' and may renumber on changed geometry, explains the highlight side effect (also returns a picture with edges in red plus a verified selector expression), and discloses the remote-server model (temporary working copy deleted when unused). It never explicitly says the call is read-only/no mutation, which is the main remaining gap.

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 purpose and the edge-record contents before filters, highlight, and remote behavior, and nearly every clause carries information an agent needs. It is dense and semicolon-heavy rather than cleanly segmented, which slows parsing of the parameter enumeration, but there is little pure 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?

For a 12-parameter tool with no output schema and no annotations, the description covers the return shape (edge fields), the highlight variant's extra returns (image + selector), and the remote file lifecycle. The unexplained `name`, `inline`, and `variant` parameters, plus no mention of the default limit of 200, keep it just short of complete.

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 largely does: kind values (line, circle, arc, ellipse, spline), the four convexity values with meanings, near ('x,y,z' within `radius` mm, nearest first), face formats (id, side, or 'x,y,z'), highlight syntax ('3,4,7', '3-6', or list), limit, part and size are all explained. Three parameters — the required `name`, plus `inline` and `variant` — are never mentioned in the description, leaving a real gap.

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?

Opens with a specific verb+resource (list the edges of a printable part) and immediately names the concrete use case (picking edges for a fillet/chamfer by id). It enumerates exactly what each edge record contains (id, type, length, endpoints/center+radius, convexity, adjacent faces), which makes it unambiguously distinct from list_faces and the other geometry siblings.

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?

States when to use it (to select edges by id rather than guessing a selector) and, critically, how to consume the result: 'put that in the script, never the ids (they change when the model changes)'. It also gives hard exclusions for remote operation ('Never use ssh, scp or a shell on the server'). It does not explicitly contrast with list_faces for the face-filtering case, so it is clear but not fully routing.

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