run_annual

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

With no annotations, the description carries the full burden. It discloses key behaviors: it runs Radiance if present, otherwise returns the exact command sequence; it automatically writes inline points to a .pts file; and it subsets the .wea when period is given. These are meaningful behavioral details beyond the schema, though it does not cover error handling or performance.

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 well-structured: a concise purpose line, then dedicated sections for channel_scenes, points, and period, followed by a single execution note. It is front-loaded with the purpose and packs significant detail without being verbose. The use of line breaks aids readability.

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?

The description covers the core inputs and the execution behavior, and references dependencies like import_geometry and run_grid. However, given the tool's complexity (11 params, simulation, no annotations), it omits explanations for several parameters and does not describe the output format, although an output schema exists. It is adequate but not exhaustive.

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 schema has 0% description coverage, so the description must compensate. It thoroughly explains channel_scenes (including the single-geometry note), points (inline vs .pts with auto-writing), and period (analysis window and subsetting). However, it leaves many other parameters (wea, run, quality, work_dir, rad_params, channel_type, timestep_min, dosimetry_threshold) undocumented, relying solely on their names. It covers the most complex required inputs but not all.

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 opening line clearly states the tool's function: 'Annual 2-phase DDS HCL simulation (per channel) -> annual mel-EDI + circadian dosimetry.' This is a specific verb+resource combination that distinguishes it from siblings like run_grid or run_image, which likely focus on standard daylight or rendering. The description also clarifies the per-channel scope and output metrics.

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 does not explicitly state when to use this tool versus alternatives such as run_grid or annual_daylight. It implies it is for HCL-specific annual simulation, but provides no exclusions or alternative routing. The final note about Radiance presence is behavioral, not usage guidance.

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