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

Beyond the annotations (readOnlyHint, idempotentHint, openWorldHint), the description adds substantial behavioral context. It discloses the exact calculation formula, the 0-500 scale semantics, the dual CONUS vs total US output scopes, the weekly temporal cadence of the source data, and the severity classification bands. This is exactly the kind of metric-interpretation context an agent needs. No contradiction with annotations; 'Retrieve' aligns with readOnlyHint=true.

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?

Roughly 90 words, organized in a clear progression: purpose, metric definition, calculation formula, output scope, and use cases. Every sentence earns its place — the formula and scale interpretation are essential for correctly interpreting results, and the use cases are the only usage-guidance content present. Dense but not bloated, with the core purpose front-loaded.

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 an output schema (return structure covered by schema), rich annotations (safety profile fully declared), and 100% parameter schema coverage, the description is complete. It covers the metric's meaning, range, formula, geographic scope, severity classification, and intended use cases. The datable range limitation is already in the schema's end_date description. Nothing an agent needs to select and invoke this correctly is missing.

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% — both start_date and end_date are fully documented in the schema, including format, maximum range, and weekly date snapping. Per the rubric baseline, the description need not repeat parameter details. It adds only marginal context (per-week granularity), which is already implied by the schema's mention of USDM weekly publication. Baseline 3 is appropriate.

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 uses a specific verb ('Retrieve') with a clearly identified resource (the DSCI for the US from the USDA/NOAA US Drought Monitor). It distinguishes itself from siblings by emphasizing that this is a single composite score at the national level, contrasting with drought.national.stats (statistics) and the county-level drought tools. The metric definition (0-500 scale, weighted sum formula) leaves no ambiguity about what is returned.

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 provides clear usage context: 'tracking drought trends over time, comparing drought years, and integrating a single drought severity metric into dashboards or alerts.' This tells an agent when this tool fits. However, it does not explicitly name sibling alternatives (e.g., drought.county.stats for county-level detail or drought.national.stats for raw statistics) or state when not to use it.

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