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

The description adds substantial mutation semantics beyond the annotations: only supplied keys change, null clears optional fields, empty string clears text but not numbers or closed lists, and required fields can be changed but not cleared. These details are important for a destructive, non-idempotent update tool.

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 compact and front-loaded: it first identifies the operation and updatable aspects, then immediately covers mutation and clearing rules. Every sentence adds actionable information without repetition.

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 annotations, nested parameters, and existing output schema, the description supplies the remaining critical mutation behavior an agent needs to call it correctly. Return values are covered by the output schema, so no description space is wasted there.

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?

With only 67% schema coverage and a nested fields object, the description compensates by explaining partial-update behavior, null-versus-empty-string semantics, required-field constraints, and when fields can be omitted. This meaningfully supplements the type-only nested schema.

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 states a specific verb and resource: correcting a registered water's name, type, mineral figures, or notes. It implies the record must already exist, which distinguishes it from register_water, but it does not explicitly name that sibling or other alternatives.

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?

Usage is implied by 'Correct a registered water' and by the note that fields may be omitted when only reason is sent. However, it does not explicitly state when to use this versus register_water or list_waters, and the water_id guidance lives in the schema rather than the description.

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