Weld Symbol (ISO 2553)

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

Annotations only declare destructiveHint=false, so the description must carry most of the behavioural burden and it does: refusals happen 'all before the first entity reaches the drawing', i.e. the operation is atomic and validation-gated, and the symbol table is deliberately truncated rather than guessed. It still says nothing about which layer/space the annotation lands in or whether existing geometry is touched, so it is not fully transparent.

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?

Two short blocks: an imperative statement of what is drawn, then a bulleted list of refusal conditions. Front-loaded, zero filler, and every clause carries information an agent needs.

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 not be described, and the 14-param schema is fully documented, so the description's remaining job is behavioural domain context, which it supplies via the refusal list and the deliberately limited ISO 2553 table. The gap is that it does not say where the annotation is placed (model space vs layout, layer role behaviour for `layer`) despite `layer` being an exposed override.

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% across all 14 params, so the schema already explains x/y, kind, side, size, pitch, and the rest in detail. The description adds only a small amount of semantics, notably the restrictions on kind, side, height and pitch. Baseline 3 is appropriate when the schema does the heavy lifting.

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 plus the standard it implements: 'Draw an ISO 2553 weld annotation: reference line, identification line, symbol, dimensions.' That is enough for an agent to know exactly what gets created. It does not, however, differentiate itself from neighbouring annotation tools such as surface_texture, centre_marks, gd_frame or datum_feature, so it stops 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 gives explicit when-not conditions: kinds outside the six shipped elementary symbols, sides outside arrow/other/both, non-positive height, and pitch without length all cause refusal. That is genuine usage guidance tied to the input domain. It never names an alternative tool for the unsupported cases (e.g. which sibling to reach for when the symbol isn't shipped), which keeps it from a 5.

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