pvsyst_run_simulation

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

With no annotations at all, the description carries real weight: it discloses write targets (Results, UserBatch/UserHourly), a non-destructive guarantee ("Existing outputs are never overwritten"), fail-early behavior on unsupported options, and critically that each run consumes a license execution. Remaining gaps are the return payload and what partial failure looks like, but the operational profile is well covered.

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 simulation mode and output-destination behavior are front-loaded, and most sentences carry operational information (overwrite policy, batch mode, license cost). It loses a point for hard-wrapped lines that split sentences mid-clause and for a trailing sentence ("Unsupported options fail early") that is light on specifics.

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 19-parameter, no-annotation, no-output-schema mutation-like tool, the description does a credible job on mode selection and side effects but is not complete: several date/report/weather parameters are never explained and there is no statement of what a successful run returns or where the agent should look next (e.g., pvsyst_read_results, pvsyst_read_batch_results).

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 19 params, so the description must compensate and only partly does: it maps the Sources naming conventions (Models SFI/RVT, Meteo MET, UserData DAT, UserBatch, Sites SIT) and explains csv_name filename-or-bare-name behavior plus the batch_params_name interaction. Entirely unaddressed are start_date, end_date, time_step, report_pages, report_language, recompute_shading, synthetic_weather, and log_level — over a third of the surface is left for the agent to guess.

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 ("Run an existing project/variant") and tags itself [Simulation], which is far clearer than a tautology. However, it never differentiates itself from the three sibling simulation entry points (pvsyst_simulate_template, pvsyst_simulate_design, pvsyst_run_house_task), so an agent cannot tell from the description alone which of those to pick.

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?

It gives one concrete when-clause tied to mode: for batch runs use batch_params_name and leave csv_name/pdf_name empty, otherwise single-run semantics apply. But it provides no guidance on when this tool is the right choice versus simulate_template/simulate_design/run_house_task, which is the dominant ambiguity for an agent given the sibling list.

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