plasticity_import_interface_fracture_csv

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

Annotations already declare readOnly/non-destructive, yet the description adds substantial context: file-type constraints (regular non-symlink UTF-8, ≤16 MiB), what it deliberately does NOT do (alter file, register test, infer failure location, correct compliance, compute cohesive law, establish allowable), and what provenance it preserves (SHA-256, record locators). This exceeds the reduced bar set by 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?

Front-loads the core purpose, then constraints, then the handoff. It is dense and every clause carries information, though several sentences are long and could be tightened without loss.

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?

With no output schema, the description supplies the missing return semantics (complete measured curves, peak and integrated work summaries, SHA-256, record locators) plus safety and input-validity constraints. Nothing essential for correct invocation is absent.

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?

Zero parameters in the schema, so the baseline is 4. The description nonetheless conveys rich semantic expectations (explicit column/unit/decimal/delimiter mapping and compliance attestation), which is helpful even though these are not expressed as schema parameters.

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 (read-only preview/import), a precise resource (per-specimen DCB Mode-I, ENF Mode-II, MMB mixed-mode traction-separation curves from a local CSV), and names the mechanism. It is clearly distinguishable from the many sibling import_*_energy_csv tools and record_*_test 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?

Explicitly states prerequisites (caller must map specimen/measurement columns, units, decimal/delimiter settings, and attest compliance-corrected data), states what is rejected (raw force-displacement), and routes the agent forward to plasticity_record_material_interface_test after review. When-to-use and the downstream alternative are both given.

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