pvsyst_compare_engineering_scenarios

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

With no annotations, the description carries the full burden and does substantial work: preview is readonly, execution writes JSON/CSV/Markdown under Results without rerunning PVsyst, unbound historical results retain needs_review, missing columns stay missing, and it explicitly avoids claiming optimality or a single cause. It omits permissions, error behavior, and rate/scale limits, so not a 5.

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 purpose, then constraints, then side effects; nearly every sentence carries distinct information. It is dense and slightly jargon-heavy, but there is little pure waste.

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?

This is a complex tool with nested objects, no annotations, and no output schema, and the description covers outputs (Chinese explanations, key-hour differences), side effects, and limitations. However the 9-field nested scenario schema is essentially unexplained, so an agent still has gaps before it can populate scenarios correctly.

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%, so the description must compensate and it only partly does: it explains the semantics of scenarios (2-3, baseline first, declared_changes) and dry_run (preview vs write), and implies objective and output_name. The nested EngineeringScenario fields (year, project, variant, csv_name, assumptions, run_manifest_name, nominal_dc_power_kw) get no explanation at all, leaving half the parameter surface undocumented.

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 names a specific verb and resource (compare two or three native result scenarios around an engineering question) and scopes the comparison to actual native columns. It is jargon-dense ('native result scenarios', 'engineering run manifests') but an agent can tell this apart from sibling read/simulate tools. It stops short of explicitly naming an alternative sibling.

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 supplies structural usage constraints (first scenario is baseline with no declared changes; two or three scenarios; each candidate declares changed input groups) and distinguishes preview vs execution via dry_run semantics. It never states when to prefer this over pvsyst_compare_components or pvsyst_read_results, so routing guidance is only implied.

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