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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is fully covered. The description adds context about the data source and that layer ids come from nfhl_layers, but does not disclose details like rate limits, response size, or pagination behavior beyond what the schema parameters already indicate. It is consistent with annotations and adds marginal value.

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 compact sentences that immediately state the purpose, list the accessible layers, provide usage examples, and point to a companion tool for layer ids. Every sentence carries critical information with no filler, achieving maximum information density in minimal 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?

For a query tool with 8 parameters and no output schema, the description covers the core usage, the typical query scenarios, and the need to consult nfhl_layers. It does not explicitly describe the response format (e.g., GeoJSON vs. features), but that is acceptable given the lack of an output schema and the tool's focus on data retrieval. The mention of pagination (offset/limit) is only implicit in the schema, not the description, but this is not a significant 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 description coverage is 100%—every parameter (where, bbox, limit, offset, layer_id, order_by, out_fields, return_geometry) has a provided description. The tool description reinforces the WHERE clause format with an example and notes that layer ids come from nfhl_layers, but does not substantially add semantic meaning that the schema already covers. Baseline 3 applies.

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 explicitly states the resource (FEMA National Flood Hazard Layer), the action (query with ArcGIS WHERE clause and optional bounding box), and enumerates the specific layers covered (flood hazard zones, base flood elevations, floodways, LOMRs/LOMAs, FIRM panels, levees, cross-sections, political jurisdictions). This clearly distinguishes it from sibling tools like nfhl_flood_zone_at_point (point queries) and nfhl_layers (layer listings).

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?

Provides concrete use cases ('every floodway polygon in this county', 'LOMRs issued on this DFIRM') and states that layer ids come from nfhl_layers, guiding the agent toward a prerequisite step. However, it does not explicitly exclude point-based queries or mention the alternative nfhl_flood_zone_at_point, though the context implies it.

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