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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context: it discloses what the response includes (canonical combos, units, exact 2019–2025 coverage, pagination, evidence hash, attribution) and the data-scope limitation (final national annual summaries vs. full catalog). This goes beyond the high-example's 3 because it specifies return contents and pagination, not just a scoping constraint.

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?

Four sentences with zero fluff: the first sentence states the action, the second lists return contents, the third gives concrete use cases, and the fourth nails the scope boundary. Every sentence carries functional information, and the most important routing guidance is front-loaded. This is efficient and logically structured.

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 simple 4-parameter search tool with no output schema, the description comprehensively covers what the agent needs: the return value shape (combinations, units, coverage, pagination, evidence hash, attribution), the scope limitations, and the use case within the broader NASS workflow (resolving series before history/trend calls). The annotations cover safety, so nothing critical 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%, so all four parameters (limit, query, offset, response_format) are already documented. The description adds minimal parameter-specific meaning; it mentions pagination (relevant to limit/offset) and gives query examples ('find durum wheat yield'), but these are light complements rather than necessary compensations. A 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 opens with a specific verb and resource ('Search LiveDataLink's self-hosted official USDA NASS Crop Production Annual Summary series') and enumerates the return contents (canonical crop/class/metric combos, units, exact 2019–2025 coverage, pagination, evidence hash, attribution). It also differentiates itself from the fuller Quick Stats catalog and explicitly names the context of resolving a series before history/trend calls, making it distinct from siblings like usda_nass_crop_history.

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 gives explicit when-to-use triggers: 'what NASS crop series are hosted?', 'find durum wheat yield', 'resolve a series before history/trend calls.' It also states a when-not-to-use boundary: scope is final national annual summaries, not the full Quick Stats catalog. The reference to history/trend calls implicitly points to sibling tools (usda_nass_crop_history, usda_nass_crop_trend), making the routing clear.

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