NDVI time series

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

Goes well beyond the readOnly/idempotent/openWorld annotations: it describes pixel averaging at 10 m, SCL-based cloud/shadow/cirrus masking, that fully cloudy dates are skipped and listed, that max_scene_cloud is a pre-filter, and the exact thresholds behind the low_confidence and suspect_dip flags. The 2-year refusal limit is also disclosed, so an agent knows the hard failure mode before calling.

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-loads what is measured and where, then layers masking behavior, output fields and limits in a compact multi-sentence block with no filler. Given there is no output schema, the enumeration of per-date fields earns its space.

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?

With no output schema, the description correctly compensates by listing per-date fields (ndvi_mean, ndvi_std, clear_pixels, clear_fraction, item_ids, flags) and by explaining skipped cloudy dates. The overall response envelope (how the per-date list and the skipped-date list are packaged) and NDVI value units/scale are not spelled out, which is the only remaining gap.

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 carry the load, and it does for most parameters: start/end format (YYYY-MM-DD), buffer_m with its 0-500 range, and max_scene_cloud as a scene-level percentage pre-filter. lat/lon are left implied, which is acceptable given they are self-evident, but the missing explicit CRS/units note keeps this from a 5.

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+scope: Sentinel-2 L2A NDVI at a point for every usable scene in a date range. It is clearly distinct from siblings like search_imagery, land_cover and elevation, since it returns a per-date NDVI series rather than imagery, classes or terrain.

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 clear operating context: single point with a buffer, per-scene cadence, and an explicit constraint that ranges longer than 2 years are refused. It does not, however, name alternatives (e.g., when to use search_imagery instead) or state prerequisites like whether the point must be over land.

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