plasticity_import_mmb_mode_i_ii_energy_csv

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

Annotations only declare readOnly/destructive/openWorld; the description adds substantial non-annotation behavior: reads only a non-symlink regular file up to 16 MiB / 250,000 records, converts force units only, preserves the CSV SHA-256 and record locator, and returns an energy-partition preview. It also explicitly states what it does NOT do (peak selection, fixture validation, evidence registration, design authorization), which is exactly the pre-call context an agent needs.

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 the core action and the file-scope constraints before the per-specimen requirements. It is dense but nearly every clause adds a real constraint; some of the closing negative list could be trimmed, but overall it is well structured.

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 an 18-param nested tool with no output schema, the description covers the purpose, inputs-in-concept, side-effect-free behavior, and explicitly bounds the returned 'preview' rather than a cohesive law. It stops short of describing the preview's payload, but the negative scope largely compensates.

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 18 required nested parameters, so the description must carry the burden. It conceptually enumerates the needed inputs (specimen ID + force column/unit/sign mapping, crack length, geometry, failure location, one-material process, sourced moduli, confirmed axis mapping), but it does not tie these to parameter names or clarify enum semantics, leaving gaps for a tool of this complexity.

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+resource ('Read-only preview of ... MMB initiation forces in one ... CSV') and scoping ('caller-selected', 'explicitly mapped local UTF-8 CSV'), which distinguishes it from the record_/read_/match_/list_ MMB siblings and from the ENF/DCB importers.

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?

Describes the workflow ('For each specimen, map its ID and force columns/units/sign, then select the exact CSV record...') and lists exclusions (never selects a peak, does not validate fixture/ASTM conformity), which implies when it applies. However, it never names an alternative sibling (e.g., the record or read MMB tools) or the condition that would route an agent there, so routing must be inferred.

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