weld_group

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

No annotations exist, so the description carries the full burden, and it does well: it spells out the direct-shear plus torsion superposition, the required_leg formula, the conditional outputs (throat_stress_mpa?, shear_sf? only when leg_mm is supplied), and the pass criterion. It stops short of confirming the operation is a pure side-effect-free calculation and omits the allowable default.

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 purpose, then mechanics, then the return-keys block; nearly every clause carries load. Density is high but appropriate for a technical calculator, with only minor compression of the units/allowable detail.

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 no output schema and no annotations, the description supplies both the return-value list and the conditional-output behavior, plus the algorithm. It is largely complete for a 6-parameter calculator, missing only the allowable default, units for allowable, and any error/failure behavior.

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 has to document all six parameters, and it explains segments tuple syntax, force_n=[Fx,Fy], load_point_mm=[px,py], leg_mm, and weld_type's 'fillet' default with units (mm, N). The allowable_shear_mpa parameter and its default of 96 are not named or explained, leaving one 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?

States a specific verb ('Rate') and resource ('planar fillet-weld group') and names the exact method (Blodgett's treat-weld-as-a-line). No CAD/FEA sibling does stress rating, so it is unambiguous even without a named alternative.

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 makes the use case implicit (feed a segment layout plus load, get a leg sizing/check), but it never states when to reach for this tool versus a FEM or other check, nor any prerequisites. Usage is inferred from the I/O mapping only.

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