Plate Check

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

Annotations declare readOnlyHint=true, and the description consistently describes a calculation-only tool. Beyond the annotations, it discloses the validity limits (thin_plate_ok: span/t ≥ 10; small_deflection_ok: δ ≤ t/2), the exactness claim ('Exact within thin-plate theory'), and the escalation behavior. It also reveals that limits are returned as flags, which is behavioral context an agent needs. It doesn't detail interpolation edge cases or failure modes, but the disclosed limits and escalation path go well beyond the annotation baseline.

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 organized: purpose first, then shape/support variants, then material inputs, then validity flags and return fields. Every sentence carries technical content. It is longer than ideal, but the density is justified by the 10-parameter schema and the need to explain the screening logic. The return-field list is somewhat long but serves as a de facto output schema since none exists.

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 10-parameter tool with no output schema and 0% schema coverage, the description is remarkably complete: it explains the formulas, the coefficient sources, the validity limits, the escalation path, and the full return payload. It does not explain what 'fidelity' or 'band_pct' mean, and it doesn't state what happens on invalid input (e.g., missing a_mm for rectangular), but the core calling context is fully covered. The missing pieces are minor relative to the tool's complexity.

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 carries the full burden for parameter meaning. It explains the role of shape ('rectangular' vs 'circular'), support ('simply_supported' | 'clamped'), and the material/youngs_gpa relationship ('E from youngs_gpa or a Materials-DB material (which also supplies yield for yield_safety_factor)'). It also explains the geometric meaning of a_mm × b_mm and diameter_mm. It does not document poisson or pressure_kpa explicitly, but those are self-evident from names and the formulas given. This is strong compensation for zero 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 opens with a specific verb and resource: 'Handbook bending of a uniformly loaded flat plate (NO solver)' and immediately frames it as a screening tool ('do I need FEM at all?'). It clearly distinguishes itself from the FEM pipeline by naming the escalation path (escalate_to='fem_run') and the sibling fem_* tools. The shape/support variants are enumerated, so an agent can tell exactly what this tool computes.

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 ('do I need FEM at all?' screen) and when to escalate: 'a tripped flag means escalate to the CCX fem_* pipeline (escalate_to='fem_run')'. It also names the alternative pipeline directly. This is explicit when/when-not guidance, not merely implied context.

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