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

The description openly discloses that the tool is not pure read-only, that the first call creates a profile and may take 30-40 seconds, that later calls may trigger LLM reordering and writes, and that it should not be polled or retried as a timeout. It also warns about private evidence content and the need for login, going well beyond 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?

Though lengthy, the description is tightly structured with clear headers (需要登录/何时用/组合链/口径/坑). Every sentence carries operational value, and the most important caveats (non-read-only, latency, no polling) are prominently flagged.

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?

The description covers authentication, return content, side effects, latency, follow-up reporting via report_growth_action_outcome, special plan kinds, and privacy-sensitive parameters. With no output schema present, it still gives the agent enough context to call the tool correctly and interpret its results.

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 for includeEvidence is already 100%, so the baseline is 3. The description adds extra operational guidance: includeEvidence=true should only be passed when the user explicitly asks for evidence, and the evidence should not be quoted verbatim. This is useful but modest on top of an already descriptive schema.

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 states a specific verb and resource: it returns the user's growth direction, current focus, blockers, and actionable steps with targetIds. It also names concrete trigger phrases (「接下来该干什么 / 下一步 / 成长导师怎么说」), making the tool's purpose unmistakable.

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 explicitly tells when to call this tool, including before advancing a user's tasks, and provides a full decision chain for what to do next per plan type (PERSON→get_creator/start_conversation, ACTIVITY→get_signup_activity→submit_signup, etc.). It also clarifies when not to report back to the platform (MENTOR_WORKSPACE items should be handled by the LLM itself).

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