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

Annotations only say idempotent and non-destructive; the description adds the real behavioral weight — a login requirement, a user-confirmation gate before writing, whole-set replacement of existing preferences, and the downstream consequence of recomputing an embedding that drives the personalized feed. Those are the facts an agent needs before mutating user data and none are derivable from 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?

Extremely economical — no filler, and the mutation's scope and its sibling boundaries come first. It leans telegraphic (fragments, "set" as shorthand), which slightly raises parsing effort, but every clause carries a distinct fact.

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 two-parameter preference-write with no output schema, the description covers auth, confirmation flow, overwrite scope, and side effects on the feed — the important gaps are closed. It stops short of describing the response or whether previous preferences can be recovered after a full replacement, which would have made it complete.

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 100% and both properties are already documented (interests: whole-group replacement, max 20; freeText: optional one-line description embedded with tags). The description's phrase "兴趣+描述" plus "更新embedding" confirms the two are embedded together, but adds no syntax, format, or constraint detail beyond the schema, so the baseline 3 applies.

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 plus resource and its exact effect: full replacement of interests and description, then embedding refresh that affects the personalized feed. It explicitly separates itself from the two nearest siblings (set_my_match_preference for match direction, set_notification_prefs for push toggles), so an agent can route 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 both the trigger sequence (get_my_profile → confirm → set) and an explicit redirect for the adjacent need (for matching, use set_my_match_preference). It also names what this tool is *not* for, which is the strongest form of when/when-not guidance in this sibling set.

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