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

Annotations already declare non-readOnly, idempotent, non-destructive and closed-world. The description adds genuinely non-derivable context: preferences affect presentation/workflow only and never scientific authority or method validity, plus the 'bounded' scope. It does not explain merge semantics for omitted or null fields, which is the main remaining gap.

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?

Two sentences with no filler; the invocation gate leads and the safety boundary follows. Nothing is redundant with the annotations.

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 nine-parameter mutation with no output schema and no field descriptions, the description should say whether this is a partial update and what happens to unspecified fields. It covers purpose and safety but leaves an agent unable to predict the effect of the call on existing preferences.

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 0% across nine parameters, so the description carries the full burden and says nothing about any individual field. It never clarifies that all fields are optional, what a null value does (clear vs. leave unchanged), or how citationStyle's free-form string is used. The self-descriptive names and four enums help, but the compensation is far too thin.

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 names a specific verb and resource (update working/writing preferences) and scopes it to a 'bounded' preference set, which separates it from memory- or profile-oriented siblings. It stops short of naming which sibling to use when the intent is to read preferences rather than write them.

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?

It gives an explicit gating condition: only call when the user explicitly states a stable preference. That is a clear when-to-use rule, though no when-not or alternative (e.g. get_profile / get_user_memory) is named for read or exploratory cases.

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