annual_nvrd

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

No annotations are provided, so the description carries the full burden. It discloses multiple behavioral traits: the pipeline is 'LONG-RUNNING', R_D is 'RELATIVE only', the tool reads site location from the EPW itself to prevent coordinate convention errors, and it explains the difference between live and emit paths (including required parameters for both). It also details the engine dependency on SMARTSPATH when physical_sky=True, and the default behavior of reconstruction.

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 description is a dense block of text but every sentence carries technical value. It front-loads the core purpose and then systematically covers the pipeline, outputs, and parameter semantics. It could be broken into bullet points for easier parsing, but it is not redundant or padded. Given the tool's complexity (17 parameters), the length is justified, though slightly intimidating.

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 tool with 17 parameters and a detailed output schema, the description covers all essential aspects: the full computation chain, output structure (faithful/enhanced R_D and RD_cum, divergence), parameter behaviors, prerequisites (points and channel_scenes), and safety note about coordinates. The output schema exists, so return values are presumably documented there, and the description even outlines them. Nothing critical is missing for an agent to call this tool 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 description coverage is 0%, so the description must compensate fully. It does: it explains reconstruction values, timestep_min default and resolution, the points parameter format (inline or .pts path), the physical_sky opt-in and its engine requirement, the run flag's behavior, and the channel_scenes requirement. This adds substantial meaning beyond the raw schema.

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 opens with a clear statement of purpose: 'Annual light-driven alertness (nvRD R_D) straight from weather (spec §5.1)'. It then details the exact pipeline and output structure, distinguishing it from generic annual simulation tools. The mention of 'SINGLE reference point+view per run' and the reconstruction options further specify scope, making it clear what this tool does and what it does not.

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 provides constraints (e.g., 'SINGLE reference point+view per run', 'run=False emits the full Daysim+Radiance command plan') but does not explicitly state when to use this tool over siblings like run_annual or nvrd. It implies usage through the detailed pipeline but lacks explicit exclusions or alternative routing, so guidance is left to inference.

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