Sheet Hem

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

The description goes well beyond the minimal annotations by explaining non-obvious behavior: the gap/radius precedence, why length_mm is measured from the bend end, that the hem reports bend allowance but no bend deduction, and that sheet_check treats it as a two-hit hem exempt from air-bend rules. This provides substantial insight into the operation's geometry and validation behavior.

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?

The description is dense but well-organized, front-loading the core purpose before explaining parameter semantics and return values. Every sentence contributes meaningful information about geometry, dimensioning, or validation. It is long, but the complexity of the hem operation and the number of non-obvious interactions justify the length.

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?

The description covers the most important conceptual and behavioral details and even names the return shape ('same dict sheet_flange does, plus {hem_kind, gap_mm}'). However, with 11 parameters, no output schema, and no parameter-level schema descriptions, the description still leaves required parameters like handle and edge unexplained and does not address parameter interactions such as direction, offset_mm, or width_mm.

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. It does explain key parameters: kind (closed/open), radius_mm/gap_mm override behavior, and the special meaning of length_mm. However, it leaves several parameters—especially the required handle and edge, plus width_mm, direction, offset_mm, and feature_name—without any semantic explanation beyond their names.

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 opens with a specific verb and resource: 'Fold a hem back on itself — the 180-degree return that stiffens a free edge and buries the sharp cut line.' It clearly identifies the sheet-metal hem operation and its purpose, and it distinguishes itself from related sheet tools by defining closed/open kind variants and explicitly excluding teardrop hems.

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?

The description implies the use case: stiffening a free edge and making it safe to handle. It also mentions how sheet_check treats the hem and that a teardrop hem is out of scope, but it never explicitly says when to choose sheet_hem over siblings like sheet_flange or sheet_tab. The guidance is mostly implicit rather than a direct when-to-use/alternative statement.

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