pvsyst_build_sfi

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the export returns native PVsyst values rather than a separate storage calculation and that some columns may legitimately be omitted depending on native run configuration. It does not state whether an existing definition is overwritten, what permissions or workspace conditions are required, or what the tool returns on success.

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?

The purpose is front-loaded in the first sentence, and the variable-specific details are relevant. However, the prose is dense, semicolon-heavy, and structured more like reference notes than a clean tool description; it also spends space on variable details while omitting the required filename parameter.

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?

There is no output schema and no annotations, so the description should be fairly complete. It covers variable semantics well enough to choose an export mode, and it explains native-value caveats, but it leaves the required filename and the creation/overwrite behavior undocumented. Adequate but with clear gaps.

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%, so the description must compensate. It gives substantial meaning for the 'variables' choices (grid_storage, soiling, grid_limit, shading) and their caveats, but it never explains the required 'filename' parameter, nor does it mention the default 'all_common'. Partial compensation only.

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 description states a specific verb and resource: 'Create a NEW hourly export definition in workspace/Models.' That is clear enough for an agent to know what the tool produces. However, it does not distinguish this tool from nearby siblings such as pvsyst_read_results, pvsyst_read_rows, or export/delivery tools, and the '[Simulation]' tag is ambiguous.

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?

The description explains which variables to select for particular review scenarios, but it never says when to use this tool rather than alternatives such as pvsyst_read_results, pvsyst_read_rows, or pvsyst_export_engineering_delivery. The conditional guidance is parameter-level detail, not tool-selection guidance.

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