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

The description goes beyond the annotations by detailing partial-update semantics: only keys sent in fields change, null clears optional fields, empty strings clear only text fields, required fields can be changed but not cleared, and capability fields use special 1/0/null conventions. This is exactly the non-obvious behavioral information an agent needs. It is also consistent with idempotentHint=true and does not contradict the 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 five dense sentences with no filler. The primary action is front-loaded, and each subsequent sentence addresses a specific, actionable nuance about updating or clearing fields. Nothing extraneous is included.

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 nested fields object and nullable enums, the description covers the behaviors that would otherwise require experimentation: partial update, clearing, required-field protection, fields omission, and capability conventions. The output schema exists, so return-value details are not required. No significant calling context 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?

With schema coverage at 67%, the description adds key meanings beyond the schema: the null-vs-empty-string clearing rules, the closed-list caveat, and the 1/0/null semantics for the three capability fields. Field names are largely self-explanatory, so the lack of per-field prose is acceptable. The description compensates for the main ambiguities without documenting every parameter.

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?

'Correct a registered scale' names the operation, target, and scope, and the following list ('type, resolution, capacity, capabilities, build or notes') specifies what can be changed. The term 'registered' distinguishes it from register_scale for new scales, though it does not explicitly call out sibling tools.

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 clearly frames the tool as modifying an existing registered scale, which is the main usage context. It also explains when fields may be omitted and how null is used to clear optional values. It does not explicitly name alternatives such as register_scale, but the 'registered' qualifier provides adequate context for an update operation.

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