pvsyst_create_load_variant

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

With no annotations, the description carries the full burden and does so: dry_run writes nothing, execution only creates a new VC (never overwrites), source VC/PRJ/CSVs untouched, no renormalization/filling/DST shift, leap-day handling, base62 DDMM encoding with returned precision, BOM disclosure for non-ASCII paths, and hard stops on legacy/ambiguous VCs. This is unusually rich disclosure of side effects and failure modes.

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, but the body is a dense run-on packing multiple distinct constraints per sentence, plus some lower-value assertions ("reading-progress logs do not prove native consumption"). No structure or grouping to help an agent scan for the rules that matter.

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 complex mutation tool with no annotations and no output schema, the description covers side effects, failure modes, and even a partial return detail (encoding precision). The main gap is per-parameter semantics and any statement of the returned VC/variant shape.

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 coverage is 0% and no property has a description, so the description must compensate for all five parameters. It explains dry_run and gives meaningful context for load_manifest_name (a prepared manifest in Results, not an absolute path), but says nothing about project, source_variant, or new_variant — three of four required params remain undefined.

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 and resource: preview/create a NEW variant with an explicit embedded hourly load snapshot, and explicitly scopes it against alternatives ("This sets loads, not battery dispatch or hybrid ports"). It doesn't name the nearest siblings (pvsyst_create_native_load_variant, pvsyst_prepare_load_profile), but the operation is unmistakable.

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?

Clear context for when to call it (bind a prepared v1 load manifest in Results to current CSVs) and when not to (don't treat config as consumed until E_User is verified in a native run; a later CSV edit needs a new binding). Lacks explicit routing to a named alternative tool for the overlapping load-variant use cases.

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