Set Preference

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes further by stating refusals occur "before any write" (atomicity/no partial mutation), enumerating validated ranges, and disclosing the headless capability requirement. It adds genuine behavioral context beyond the annotations, though it does not discuss auth beyond the capability gate.

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?

Front-loaded with purpose, then a tightly grouped refusal clause; nearly every phrase carries information. The trailing "Pack: settings · lean: no." metadata is terse and unexplained, a small amount of noise, keeping it from a 5.

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?

The tool has an output schema, so the description need not explain return values, and it still notes the old/new/changed report and all pre-write validation gates. For a 2-parameter mutation with full schema coverage and annotations, this is essentially complete, with only the get-then-set workflow left implicit.

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 coverage is 100%, so the baseline is 3, but the description supplies concrete range semantics the schema omits (AutoSaveInterval 0–600 min, CursorSize 1–100, PickBoxSize 0–50, enum SaveAsType names). That meaningfully enriches what is otherwise a generic bool/int/string/enum 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?

States a specific verb+resource ("Write one preference") and its report contract, and the singular scoping ("one preference") distinguishes it from a bulk settings writer. The existence of sibling system_preferences_get makes the read/write split legible immediately.

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 refusal list is excellent when-not guidance: read-only keys, unknown keys, wrong type, out-of-range ints, unknown SaveAsType, and headless/capability conditions are all enumerated. It does not, however, name an alternative or explicitly instruct the agent to source keys from system_preferences_get (only the schema hints at that), so it stops short of a 5.

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