Mechanical: Add View

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

Annotations only supply destructiveHint=false; the description adds substantial behavioral context beyond that: the XDATA lookup, the default first-angle projection convention ('the view from the right goes to the left'), and a detailed catalogue of rejected inputs with the reason messages. It does not state whether the drawing is modified or how the new view is named, but the coverage is well above the annotation baseline.

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 core concept, then the XDATA source, then the refusal list. The refusal enumeration is long but each item is substantive; the prose is slightly literary ('laid out on its projection axis') but not wasteful.

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 an output schema present, return values need no explanation, and the description covers usage context, defaults, and failure modes for an 8-parameter optional-all tool. Minor gaps remain (e.g., whether the view is created on the current layout, what happens to existing views), but the agent has enough to invoke correctly.

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 100%, so baseline is 3. The description reinforces cross-parameter constraints (plane required for a section, detail.scale vs view scale, part_id omission when the drawing holds one part), but these largely restate the schema's own notes rather than adding new syntax or format detail.

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 states a specific resource (another view of an existing part) and its placement behavior, and the projection-axis framing differentiates it from siblings like mech_part_draw and mech_dimension_part. The verb 'add' comes only from the name, and the opening sentence is descriptive rather than action-framed, so it falls short of a 5.

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?

It explains the operating context (part comes from ACADMCP_MECH XDATA, caller never re-describes it) and enumerates precise refusal conditions: section without a plane, zero-length or missing plane, wrong plane style for half/offset, detail without radius, unknown part_id, ambiguous part_id=None. This is strong when-to-use/when-rejected guidance, though it never names a sibling alternative to use instead.

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