plasticity_record_material_interface_test

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

With annotations only marking it non-read-only/non-destructive, the description carries real behavioral weight: immutability, idempotency on repeated identical data, the callerConfirmsPhysicalTests attestation, validation rules (curves begin at zero, end at zero traction, match the evidenced peak), load-alignment constraints, and that depositionPathEvidence is provenance only and never converted to strength. These are traits annotations cannot express.

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?

Purpose is front-loaded and nearly every sentence encodes a distinct required rule, so the length is justified by the tool's complexity with almost no filler. It is delivered as one dense block with long multi-clause sentences, which hampers scannability of the conditional branches and constraints.

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 22-parameter, nested-object, mutation-style tool with no output schema and no schema descriptions, the description supplies the domain rules an agent needs (fracture-method-to-loading-to-curve-type mapping, curve endpoint and peak-matching requirements, provenance-only status of deposition path evidence, idempotency). It omits any indication of what is returned on success and leaves the evidence-array and hash/protocol parameters unelaborated.

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% across 22 parameters, so the description must compensate, and it explains the identity fields of materialProcess (printer/material/profile/orientation/infill percentage/pattern/wall-loop/top-bottom-shell/nozzle-temperature/layer-height), the global normal and load direction, fractureMethod enum values, the per-specimen fields, the representativeSpecimenId-to-peak match, and the depositionPathEvidence contents. Several parameters (testProtocolHash, the evidence array, notes, testedAt, source, specimenCount, callerConfirmsPhysicalTests) are left unexplained, so it does not fully close the zero-coverage gap.

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 first sentence states a precise verb (Store) and resource (an immutable caller-attested physical test of a printed layer interface) with explicit scope ('one material and one exact print process shared by both sides'). It also draws a boundary against the sibling plasticity_calculate_interface_specimen_strengths and against designing/approving, so an agent can place it among record/match/list/analyze siblings without opening schemas.

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?

It gives clear conditional routing: 'For a direct peak-strength series... attach one specimenResults entry', 'For a curve-based fracture test, explicitly set fractureMethod', and 'A direct-strength record without a traction-separation curve must include these raw specimen results,' plus a pointer to plasticity_calculate_interface_specimen_strengths for derivation. It stops short of naming the retrieval/analysis siblings (match/list/analyze) as alternatives or stating when NOT to record.

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