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

The annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds the partial-update semantics: 'Only the keys you send in fields change' and explains how to clear fields with null or empty strings. It also mentions the behavior of the 'reason' parameter, which is valuable beyond the schema. No contradiction with annotations.

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 a single dense paragraph with key behavior front-loaded ('Only the keys you send change'), and it covers multiple important details without being overly verbose. It could be broken into bullet points for clarity, but the flow is logical.

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?

Given the complexity (nested object, partial updates, null clearing) and the existing schema descriptions for water_id and reason, plus annotations covering idempotency, the description covers the essential behavioral rules. The output schema exists, so return value details are not needed. The only small gap is that it doesn't explicitly mention that 'fields' is optional, but that's implied by 'may be omitted' for reason, and the schema doesn't mark it required.

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 67%: water_id and reason have descriptions, but the 'fields' nested object has no overall description. The description clarifies the semantics of 'fields' (partial update, null clearing), which compensates for the schema gap. However, it doesn't provide details on each individual field (gh, kh, tds) beyond names, which are self-explanatory. So the description adds moderate value.

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 states the verb 'Correct' and resource 'a registered water', and lists the modifiable fields (name, type, mineral figures, notes), so an agent understands the tool's core function. However, it doesn't explicitly differentiate from sibling tools like update_bean or update_machine, though the resource is explicit in the title.

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 guidance on when to use this tool relative to others: it corrects an existing water, implying it should be used after listing or registering a water, and mentions list_waters in the schema. It doesn't explicitly state when NOT to use it or name alternatives, but the context is clear enough.

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