rb209_recommendation_recommendations

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

With no annotations, the description carries the full burden and does substantial work: it warns about the misleading 422 error when field.grass is missing, reveals that the server auto-fills empty objects, explains the cropInfo2Id effect on K, and says the call returns all requested nutrients at once. It omits details like response structure and side effects, but it surfaces the most important non-obvious behaviors.

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 dense and front-loaded with the purpose and endpoint, then moves through prerequisites, call count, arable-body requirements, soil-analysis handling, and key parameters. Every sentence carries useful guidance, though the flowing em-dash style could benefit from bullet formatting. It is long, but justified given the complexity of the request body.

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 deeply nested, complex endpoint with no output schema and no annotations, the description should explain both request construction and return interpretation. It covers the arable case, no-soil-analysis case, and several pitfalls, but it does not explain the response shape, how to interpret the returned values, or how to construct the body for grass/mixed fields. The guidance is strong but incomplete for the full range of inputs the schema supports.

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?

Although the signal reports 0% schema description coverage, the nested schema actually contains detailed property descriptions. The description adds real value beyond the schema by giving concrete values for cropInfo2Id (1 = straw baled/removed, 2 = straw incorporated), specifying field.grass = {} and field.grassland = {} for arable fields, and explaining soilAnalyses = [] when no soil data exists. It does not add semantics for totals or referenceValue, but the most error-prone fields are covered.

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 clearly identifies this as the main endpoint to "calculate nutrient recommendations" and specifies the HTTP path. It also states what it returns — every enabled nutrient — which distinguishes it from per-nutrient calls. However, it does not explicitly contrast it with sibling recommendation calculators like calculate_nutrient_offtake or calculate_nutrient_deficiency, so differentiation is implied rather than explicit.

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 strong operational guidance: collect all inputs first, call once, do not call per-nutrient, use rb209_rainfall_average for rainfall, skip lookups when there is no soil analysis, and always ask for cropInfo2Id. It does not explicitly say when to choose a sibling recommendation tool instead, but the when-not guidance is clear enough for the core workflow.

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