design_for_load

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

No annotations exist, so the description carries the full burden. It usefully discloses the paid-tier entitlement requirement, but says nothing about what actually happens when called without Kiln Pro (error, stub, upgrade prompt), what the verdict response contains, or whether any computation occurs at all. The "would compute" phrasing actively obscures runtime 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?

Compact and front-loads the verdict concept, but two of four lines are marketing/upsell material ("Kiln Pro would compute...", pricing URL) that consume space without helping an agent decide or call. Tighter than most, but the hypothetical framing wastes the strongest position.

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?

An 18-parameter structural analysis tool with a nested cross_section_mm object, no output schema, and no annotations needs the description to explain inputs and results. Instead it explains neither, and doesn't clarify the tier-gate behavior — leaving the agent unable to predict either the call contract or the return.

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?

With 18 parameters at 61% schema coverage, several inputs (load_n, length_mm, cross_section_mm, application_class, cycle_count, print_orientation) are undocumented. The description adds zero parameter meaning — nothing on units, valid cross-section shapes, or how mode/application_class interact with the derate chain, which is exactly what an agent would need to call this correctly.

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?

"Cantilever bending design verdict with FoS + derate chain" names a specific analysis output and distinguishes it from broader siblings like analyze_structural_risks or assess_load_bearing. However, the framing "Kiln Pro would compute the load verdict" makes it ambiguous whether this tool performs the analysis at all or merely returns an upsell, which undercuts purpose clarity.

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 only selection guidance is "Requires Kiln Pro" — an entitlement condition, not a when-to-use rule. No mention of when to prefer this over estimate_structural_load, assess_load_bearing, analyze_frame_bracing, or record_load_outcome, among the many structural siblings in the catalog.

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