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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low; the description instead adds the interpretive behavior that matters — null means BNPB maps no hazard (dry ground or sea), 100 m cells, national model rather than a historical flood record. That is substantive context an agent cannot get from structured fields.

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?

Purpose and class semantics are front-loaded, and nearly every sentence carries distinct information (classes, input format, sibling alternative, null meaning, accuracy caveat). It is one dense paragraph with a slightly crowded middle sentence, but nothing is 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?

There is no output schema, so the description must explain return values, and it does: the three kelas values, the underlying 0-1 index and its cut points, and what null signifies. Combined with the accuracy caveats, an agent has everything needed to call and interpret it.

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 100% and the schema already documents 'latitude, longitude', so the baseline is 3. The description earns an extra point by supplying a concrete example pair (-6.4601, 107.0093), which removes ordering ambiguity, though it adds no new constraint or edge-case handling.

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 (BNPB InaRISK flood hazard at a location) and immediately defines the return vocabulary (kelas 1 rendah, 2 sedang, 3 tinggi) with the index cut points. It also names the sibling that serves a different scope (Parcel_get's banjir for a whole parcel), so an agent can distinguish it without opening either schema.

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?

Explicitly routes: use Parcel_get's banjir for a parcel, use this for a single location. It also gives the when-not condition ('screen a location, not judge a single plot') and warns that null is not proof of no flooding, which is exactly the misread an agent could make.

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