Molding Screen

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

Annotations provide readOnlyHint=true, and the description aligns by stating 'NO solver'. It adds rich behavioral context: fidelity values ('exact' vs 'correlation'), band_pct=30 for the correlation, and the escalate_to field that routes to a solver. It also describes that cooling remains exact even when flow_length is added, clarifying mixed-fidelity behavior. No contradiction with annotations.

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 and technical, containing a formula, material list, conditional behavior, and return fields. It is structured in a logical flow (purpose, formula, conditions, escalation, outputs) and every sentence adds value. It could be slightly trimmed, but given the tool's complexity, the length is justified and 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?

For a complex tool with 8 parameters, no output schema, and no schema descriptions, the description covers most essential context: formula, materials, fidelity, escalation, and return fields. It lists all return fields but does not explain semantics for some (e.g., valid_range_ok, warnings). Also flow_ratio_limit input semantics are not fully clarified. Still, it is largely complete for an agent to call 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?

With 0% schema coverage, the description compensates well. It explains material (per-polymer defaults, individually overridable), wall_thickness_mm as the s in the formula, alpha_mm2_s as α, temps (T_melt, T_mold, T_eject), and flow_length_mm. It also clarifies when material is unnecessary. However, flow_ratio_limit is not explicitly described as an input parameter, and its role in the fill check is only implied via 'L/t-limit'. This is a minor gap given 0% schema coverage.

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 clear, specific purpose: an injection-molding screening tool that computes a one-term cooling time and optionally a spiral-flow fill check, explicitly labeled 'NO solver'. It distinguishes itself from siblings like molding_fill_submit (the VOF fill solve) and molding_warpage_submit by noting it is a screen, not a full simulation, and even names the escalation target.

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 gives explicit usage conditions: 'cooling-only call' vs 'adding flow_length_mm', and instructs that when flow_length_mm is given the headline check is a correlation and should escalate to molding_fill_submit, while a cooling-only call needs no solver. It also notes that if all temps and alpha are explicit, no material is needed, guiding parameter use.

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