set_my_preferences【需要登录】设置当前用户的兴趣标签（+ 可选自由描述），用于计算兴趣向量、驱动 personalized_feed 的千人千面排序。一句话即可调教推荐，是个性化读写闭环的写入端。整组替换。
| Name | Required | Description | Default |
|---|---|---|---|
| freeText | No | 一句自由描述（与标签一起 embed），可选 | |
| interests | Yes | 兴趣标签（整组替换，最多 20 个） |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotence, and destructiveness; the description adds a crucial non-obvious behavior: the whole interest set is replaced ('整组替换'), not merged. It also discloses the login requirement and that freeText is embedded together with tags. No contradiction with 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 compact and front-loaded: login requirement first, then the action, then downstream use, then replacement semantics. A few marketing-style phrases ('一句话即可调教推荐', '千人千面排序') add flavor but are not strictly necessary, keeping it just below a perfect 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?
For a low-complexity setter with rich schemas and annotations, the description covers auth, purpose, relationship to personalized_feed, whole-group replacement behavior, and optional freeText handling. An output schema is unnecessary for this simple write operation, and no critical information 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?
Schema already documents both parameters with 100% coverage, so the baseline is 3. The description adds meaningful semantics: interests are replaced as a whole set, freeText is embedded with tags, and the interaction with personalized_feed is clarified. This goes beyond what the schema alone provides.
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?
Description names a specific verb '设置' and resource '当前用户的兴趣标签', plus optional free text, and explains its downstream effect on personalized_feed ranking. This clearly distinguishes it from its read counterpart get_my_preferences.
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 states it requires login and positions the tool as the write side of the personalization loop that drives personalized_feed, so an agent can infer when to invoke it. It does not explicitly mention get_my_preferences as the read alternative or state exclusions, so it falls just short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly documented purpose, often with explicit 'when to use' guidance and cross-references, making the vast majority easy to tell apart. A few clusters (get_my_brief, get_my_positioning, get_my_work, get_my_dispatch) and data-overlapping get_my_card vs get_my_profile require careful reading, but descriptions are detailed enough to prevent serious misselection.
The overwhelming majority follow snake_case verb_noun conventions (create_product, update_need, list_my_signups). Minor deviations include noun-only feed names (personalized_feed, random_feed), inconsistency between 'prefs' and 'preferences' in notification tools, and a mix of update_* and set_* for mutations, but the pattern remains predictable overall.
137 tools is an extreme mismatch for any MCP server, far exceeding the 50+ threshold for a score of 1. Even with a broad multi-domain platform, this volume makes tool selection and navigation impractical and heavily burdens the agent's context window.
The surface covers full lifecycles for needs, products, activities/signups, conversations, collaboration goals/tasks, dispatch, profile/onboarding, and supporting resources like companies, parks, policies, and ratings. Deliberate omissions (no user-post creation, no organizer profile editing via agent) are explicitly documented, so core workflows have no obvious dead ends.