pvsyst_read_house_pv_scene

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

With no annotations, the description carries the full load and does so richly: original file never overwritten, no project/native scene edited, import/native_consumption_verified stay false, no geometry auto-repaired, bounded UTF-8 XML reads with DTD/entity declarations stopping execution, and needs_context for missing provenance. These are exactly the safety and side-effect disclosures an agent needs.

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 and every sentence is substantive, but the block is dense and crams security/XML-parsing caveats alongside the workflow, making it harder to scan. Slightly long for a one-parameter reader, though little is genuinely wasted.

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?

No output schema and no annotations, so the description must carry return semantics; it names key returned artifacts (create_arguments, needs_context, required_inputs) and constraints. It stops short of describing the full shape of create_arguments or the success return, leaving some gaps for an agent composing the downstream create call.

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?

The sole parameter scene_name has 0% schema coverage and the description only hints at it via 'UserData/*.pvc2' — it never clarifies whether scene_name is a bare name, a relative path, or a full path. The description does add value about a related field (required_inputs always includes output_name), but the actual input parameter remains ambiguous.

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 ('Read a generated UserData/*.pvc2 back into complete house/PV create arguments') and clarifies the transformation (parse XML mesh vertices/triangles and module dimensions, rebuild dialect). It also explicitly excludes siblings/alternatives ('not a general COLLADA converter or a native VC scene exporter') and points to pvsyst_create_house_pv_scene, so an agent can distinguish it from import/create tools.

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 an explicit workflow: take returned create_arguments, modify parts/layout, supply a NEW output_name, then preview/create with pvsyst_create_house_pv_scene. It also states a when-not ('not a general COLLADA converter or native VC scene exporter') and notes the old-R44/no-provenance case returns needs_context rather than guessing.

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