list_faces

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

With zero annotations the description carries the full burden and does so: id stability rules ('1 = the largest; same geometry always gets the same ids, changed geometry may renumber'), the fact that curved faces are only counted not listed, remote-server file semantics (temporary working copy, download_part zip layout), and a hard constraint against ssh/scp. This is behavior an agent could not infer from 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-loaded with the resource and its record fields, then parameters, then remote-server caveats — a sensible ordering. It is dense and parenthetical-heavy with a couple of run-on sentences, but nearly every clause carries operational information rather than 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 six-parameter read tool with no output schema, the description explains the returned face record fields and the remote-file lifecycle, which is the important part. The unexplained name/inline/variant parameters and the unspecified output shape of the highlight image are the remaining gaps.

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 only partly does: part, highlight and size are explained with defaults and accepted values, but name (the sole required parameter), inline and variant get no mention at all. Three of six parameters remain undocumented anywhere.

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 ('The flat faces of a printable part') and enumerates exactly what each face record contains (ids, normal, side, area, center, bbox, holes). It is clearly distinguishable from sibling list_edges and from make_template, which it explicitly feeds.

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 the downstream purpose ('for picking one for a face fit-test template (make_template kind='face')') and prescribes the confirmation loop via highlight before making the template. No explicit when-not-to-use or named alternative for someone who actually wanted edges, so 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.