Verify values at a point

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description correctly spends its words elsewhere: it discloses that computation is done 'directly from the raw bands on the scene's native grid' and that it returns pass/warn/fail with per-check detail. It omits cost/latency expectations for raster reads and what happens when no clear scene exists in the window.

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?

Three front-loaded sentences with no filler; the purpose and the three checks are stated before the return contract. Dense but every clause carries information, though the middle sentence packs multiple checks into one long clause.

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, but the description supplies the return contract (pass/warn/fail plus per-check detail) and names all three checks. Remaining gaps — coordinate conventions, behavior when no clear scene is found, and cost — keep it short of complete for a comparison tool that touches multiple raster products.

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 compensate. It does explain `days_back` well ('latest clear scene (last days_back days)') and implies lat/lon via 'at a point', but says nothing about coordinate order, CRS, or the default of 120 days — so compensation is only partial.

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 — 'independent sanity checks at a point' — and enumerates exactly what is checked: NDVI recomputed from raw B04/B08/SCL bands vs. the ndvi_timeseries pipeline, native vs. regridded elevation and land cover, and land cover vs. NDVI. This clearly distinguishes it from the sibling generation tools (ndvi_timeseries, land_cover, elevation) by framing it as a cross-validation step.

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?

Usage is only implied: the phrase 'independent sanity checks' and the explicit comparison with the ndvi_timeseries pipeline suggest it should be used after those products exist, but there is no explicit when-to-use/when-not statement or named alternative. An agent must infer the trigger condition.

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