相关会话推荐

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

No annotations are provided, so the description carries the full burden. It discloses that recommendations are algorithmic rather than explicit links and are navigation hints only, not authoritative content. This is useful trust and accuracy context, but it does not cover what a result contains, such as scores or reasons for relevance, or whether project scoping is required.

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 front-loaded with what the tool does and then lists when to use it, with zero filler. The Chinese phrase "何时用" device is compact and scannable, though the sentence is dense and packs three use cases plus a caveat into one line.

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 recommendation tool with no output schema and no annotations, the description covers purpose, triggers, and result trust level. It could say more about what a recommendation entry contains, but nothing an agent needs in order to call it correctly 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 description coverage is 100%, so limit, project, and session_id are already documented in the schema, including the prefix support for session_id and the unresolved_project trigger for project. The description only implies that session_id is the anchor and adds no syntax or format detail beyond the schema. Therefore, the baseline of 3 is appropriate.

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: recommending related historical sessions for a given session. The key differentiator, "算法发现，非显式关联", explicitly distinguishes it from link_sessions and get_linked_sessions if those tools return user-created explicit links, so an agent can tell the two apart without opening the 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 names three concrete use cases: browsing a session to find related discussions, finding attachable history before starting a new session, and finding leads through a session when keywords cannot be recalled. The implicit contrast is against keyword search. The caveat that content is authoritative via get_session_detail also tells the agent what not to use this tool for.

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