pvsyst_prepare_load_profile

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

No annotations are provided, so the description carries the full burden and does so: dry_run=true writes nothing, the source is preserved, an ASCII Date;P Load / ;kW CSV is written to UserHourlyParams plus an import record to Results, existing names are preserved, and write failure retains partial outputs. Failure semantics are enumerated precisely (missing/duplicate/non-hourly/negative/nonfinite rows stop) along with what is deliberately NOT done (no gap filling, resampling, renormalization, net-meter interpretation, or time shift).

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 in the first clause and nearly every sentence adds distinct information. Density is high and some sentences stack multiple constraints, but there is little true filler — the main cost is a slight kitchen-sink feel that makes skimming harder.

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 9-parameter, 0%-schema-coverage, unannotated mutation tool with no output schema, this covers inputs, validation rules, side effects, output locations, failure behavior, and the downstream step required to actually use the produced CSV. An agent has enough to invoke it correctly and to know what it must do next.

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 9 parameters, so the description must compensate and largely does: it explains the date column and load column expectations, accepted date formats (iso, pvsyst_dot, pvsyst_slash) with literal examples, the whole-hour UTC offset with no DST, the 8760/8784 interval-start hour basis, and dry_run behavior. The output_name parameter is never explained, which is the main remaining 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?

Opens with a specific verb+resource+scope: 'Inspect or prepare a NEW native hourly load CSV from workspace/UserData.' It then explicitly separates this from native consumption ('ready/prepared concern this CSV only... bind the CSV to a variant') and distinguishes it from the input-param-file DAT channel, so an agent can tell it apart from siblings like create_load_variant or create_native_load_variant.

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?

Gives a clear use context (inspect or prepare), the preconditions that must hold, and an explicit exclusion ('input-param-file is an advanced parameters DAT, not a load CSV channel') plus a required follow-up step. It stops short of naming an alternative sibling tool by name, so routing is implied rather than prescribed.

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