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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it returns per-interval mean/min/max/stdev, uses Sentinel-2 imagery, and explicitly states 'Derived numbers only, no imagery', which clarifies return behavior beyond the schema.

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 two sentences plus a realistic example. The first sentence states the core purpose, the second adds the key 'no imagery' distinction, and the example demonstrates a complete valid call. Every element earns its place without redundancy or filler.

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 6 parameters, a nested geometry object, and no output schema, the description covers the essential points: input area and time range, aggregation, derived statistics, and the derived-only nature of results. It does not mention potential quirks like cloud coverage, Sentinel-2 data availability, or output formatting, but these are not critical for a read-only stats 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?

Schema description coverage is 100%, so the baseline is 3. The description's inline example illustrates parameter usage (bbox order, date format, aggregation, _apiKey format), but it largely duplicates what the schema already explains. It does not introduce meaning beyond the schema for any parameter.

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 states a specific verb ('returns'), resource (NDVI vegetation statistics from Sentinel-2 imagery), and scope ('over an area and time range'). It also distinguishes itself from imagery-returning tools by explicitly saying 'Derived numbers only, no imagery', which separates it from siblings like sentinelhub_catalog_search.

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 implies its use case — computing NDVI statistics over a bbox/GeoJSON area and date range — and gives a concrete example. However, it does not explicitly tell an agent when to prefer this tool over alternatives such as sentinelhub_catalog_search, nor does it state any exclusions or conditions.

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