FSI Plate Deflection

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the safety profile is already covered. The description adds valuable behavioral context: it is a closed-form calculation (no solver), it returns a rich result set including fidelity, band_pct, valid_range_ok, warnings, and escalate_to, and it explicitly states the validity limit (δ ≲ thickness). It does not describe failure modes or edge cases (e.g., what happens if material and youngs_gpa are both missing), but the annotations plus the validity-range disclosure carry most of the burden. A 4 is appropriate because the description adds meaningful behavioral context beyond the annotations without contradicting 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?

The description is dense but well-organized: it opens with the core purpose and solver-free nature, then explains the physical model, then the support-specific formulas, then the validity limit and escalation path, and finally the return fields. Every sentence earns its place. It is longer than a typical description, but the complexity of the tool (8 parameters, two support conditions, a validity gate) justifies the length. A 4 because it is slightly long but highly structured and information-dense.

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?

Given the tool's complexity (8 parameters, two support conditions, a validity gate, and a rich return set), the description is remarkably complete. It covers the physical model, the formulas, the validity limit, the escalation path, and the return fields. There is no output schema, so the description's listing of return fields is valuable. Minor gaps: it doesn't specify units for all return fields (e.g., `line_load_n_per_mm` is clear, but `band_pct` and `fidelity` are not explained), and it doesn't state what happens if both `youngs_gpa` and `material` are omitted. These are small gaps against an otherwise thorough description, so a 4 is fair.

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 0%, so the description must compensate. It does: it explains the physical meaning of `pressure_pa` (fluid pressure acting normal to the strip, giving line load q = pressure·width), `width_mm`×`length_mm` as the wetted strip, `i_mm4` as an explicit second moment of area overriding the default I = width·thickness³/12, `youngs_gpa` or `material` as E sources, and `support` with its two enum-like values ('cantilever' and 'clamped-clamped') and their formulas. This is substantial semantic enrichment. It doesn't document every parameter (e.g., `thickness_mm` is implied but not explicitly described), but the coverage is strong enough for a 4.

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 specific verb ('deflection'), a precise resource ('thin plate strip'), and the exact scope ('small-deflection tip/centre deflection of a uniform-pressure-loaded thin plate strip'). It explicitly distinguishes itself from the coupled FSI solve by naming the sibling tool `fsi_pressure_plate_submit` and positioning itself as the closed-form twin. This is a clear, specific, and well-differentiated purpose.

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 explicitly states when to use this tool: for exact small-deflection closed-form results without a solver, and when to escalate: 'past that escalate to an NLGEOM follower-pressure ccx solve.' It also names the alternative tool (`fsi_pressure_plate_submit`) and frames this tool as the gating check. This is explicit when/when-not guidance with a named alternative.

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