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

The description adds genuine value beyond the annotations by disclosing partial-merge semantics ("Only the keys given change"), which is not implied by idempotentHint alone. However, annotations declare destructiveHint=true and the description never explains where the destruction lies — the retention setting deletes chat history and pins replaces the entire list — nor does it note that the write is self-scoped. For a destructive mutation the risk disclosure is thin.

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 verb and resource, then the field list, then the two behavioral clauses (partial update, language exclusion) in short sentences. The long enumerative clause is dense but each item maps to a real parameter; a slight trim of fields already fully documented in the schema would improve it.

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 13-parameter tool with a nested profileVisibility object, an output schema, and full annotations, the description covers scope, merge behavior, and the main sibling boundary adequately. Remaining gaps are the unlisted toast position/limit settings and the absence of any warning that retention and pins cause data loss/replacement.

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 85%, so the baseline is 3 and the schema already carries most parameter meaning. The description's prose enumeration largely restates parameters ("sidebar position and auto-hide", "collapsed nav", "who sees each profile field") and actually omits toastPosition and toastMaxVisible, so it adds little syntax or constraint detail the schema does not already have.

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 ("Change") and a precisely scoped resource ("the user's own preferences"), then enumerates the concrete settings covered (theme, calendar, start page, dock, presence, toasts, retention, pins, profileVisibility). It also names the boundary against a sibling ("Language is not here: use language.update"), so an agent can distinguish it from language.update and preferences.read without opening any schema.

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?

Gives an explicit exclusion plus alternative for the most confusable case (language settings → language.update) and states the partial-update contract ("Only the keys given change"), which is the key usage rule. It stops short of routing against other adjacent tools such as profile.update, member.update_profile, notifications.update, or working_hours.update, which overlap in subject matter.

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