Moldability Screen

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

With only readOnlyHint and openWorldHint annotations, the description carries the behavioral burden and does so thoroughly: no solver/geometry, graceful degradation when corpus fields are missing, semicrystalline resins flagging model_underpredicts, threshold values, and the shrinkage formula. It adds substantial context beyond the annotations and does not contradict them.

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 a strong first line and organized into numbered checks, formulas, and a return-key list; nothing is fluff. The density of information makes it a somewhat heavy block to scan, but the structure helps navigation.

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 tool with no output schema, the description gives inputs, formulas, degradation behavior, escalation guidance, and a return-key list, which is strong. Still, return values like band_pct, score, and fidelity are only named, not interpreted, so some output semantics must be inferred.

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 description coverage, the description compensates well: wall_samples are given units, warn/fail thresholds map to warn_ratio/fail_ratio, sink_factor is explained via k≈1.5, and alpha·ΔT grounds alpha_per_k/t_ambient_c/t_solidify_c. However, t_ambient_c/t_solidify_c and nominal_mm units are only implicit, and the exact parameter names are not explicitly linked to their meanings.

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 and resource: a 'Moldability DFx screen' with 'NO solver, NO geometry' and a 'fast analytic gate'. The description names the two concrete checks (wall-thickness quality and shrinkage), so an agent can distinguish it from full molding/fill simulation tools.

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?

Clearly frames when to use it: as a low-fidelity analytic gate, with escalation to 'molding_fill_submit' for higher-fidelity work. It also states what it is not ('NO solver, NO geometry'), though it does not explicitly contrast with similarly named siblings like molding_screen or moldability_check.

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