pvsyst_build_sourced_component

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 thoroughly: it discloses that dry_run performs no writes and returns provenance/inherited params/diff, that creation writes a new component plus a Results source record, that existing paths are never overwritten, that a failed creation rolls back the source record so retries are safe, and that outputs remain needs_review rather than certified. It even scopes what is not certified (datasheet authenticity, layout, model applicability).

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 and safety-critical behavior are front-loaded, and every sentence addresses either scope, parameter semantics, or write safety. It is dense but not padded; minor redundancy like repeating 'never overwrites existing paths' twice keeps it from a 5.

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 10-parameter, nested-object, unannotated mutation tool with no output schema, the description covers behavior well but leaves significant parameter-level gaps: the structure of sources/declarations, what template_name expects, and the meaning of source_library enums are not described anywhere. An agent could not construct nested payloads from this description alone.

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, and it does partially: it explains PAN vs OND field sets with units (PNom W, ISC/Imp A, Voc/Vmp V; PNomConv kW, VMppMin/Max/V, EfficMax/Euro %), dimension/weight units, and the acknowledge_inherited_model requirement. But 10 parameters including nested sources/declarations objects and enums (source_library, component_type) are not fully addressed — template_name, new_name, manufacturer/model, and how source map keys bind to declarations.source_id remain unexplained.

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+resource: 'Preview or create a NEW user-defined PAN/OND from a complete exact template and cited values.' This is clearly distinguishable from generic component creation because of the template-plus-citation framing. However, it never names the nearest siblings (e.g. pvsyst_create_component) to make the boundary explicit.

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 operating context: dry_run defaults to preview with no writes, and actual creation requires acknowledge_inherited_model=true. It also states the verification path ('Use a referencing native run to verify behavior'). It stops short of explicit when-not-to-use or naming alternative tools such as create_component.

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