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

The readOnlyHint annotation already covers safety, and the description adds real behavioral context: the dual ranking strategy, the fallback trigger, the login precondition, and the deck-continuation semantics of the cursor. It does not describe what a feed item contains or how large the deck is, which keeps it below a 5.

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?

A single compact paragraph with no filler: purpose first, then ranking/fallback rules, then sibling comparison, then pagination contract. Every clause carries information an agent needs.

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 read-only, two-parameter feed tool with no output schema, the description covers personalization logic, fallback behavior, login precondition, and pagination. The only gap is that it never says what the feed items are or pagination termination, which is minor since no output schema exists to defer to.

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% and both parameters are documented, so the baseline is 3. The description adds meaning beyond the schema by explaining that the cursor must be echoed back verbatim to continue the same deck (同一副牌), which clarifies why a client must not synthesize or reset it.

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 ('返回千人千面的发现 feed') and immediately scopes it with two distinct ordering modes (interest-semantic vs. claimed-first + popularity). It also explicitly contrasts with the sibling random_feed and positions itself as the default post-login discovery page, so an agent can distinguish it 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?

It gives the exact condition that changes behavior: when the user is logged in and has set interests via set_my_preferences, otherwise fallback. It names the alternative (random_feed) and states the selection criterion ('更贴合用户口味'), and it tells the agent this is the default discovery surface after web login.

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