Select an action for an AI agent using its personality baseline and feedback-learned preferences. Optionally accepts a candidate list to choose from, otherwise uses the agent's own action pool.
让 PASM 按「人格基线 + 反馈学到的偏好」从动作池里选一个动作。不传 candidates 就用智能体自己的动作池。
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | No | default | |
| candidates | No | 候选动作列表（可选） |
Changes observed during successful MCP inspections.
v0.2.0Does 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 the selection mechanism (personality baseline + learned preferences) and the candidates fallback behavior, but doesn't disclose side effects, whether this mutates state, whether it records the choice, or what the return value looks like.
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?
Two sentences, front-loaded with the core purpose and selection criteria. The conditional usage note is placed efficiently. No wasted words.
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 tool with no annotations and no output schema, the description is thin. It doesn't explain what the returned action looks like, whether the selection has side effects (e.g., storing feedback), or how it relates to sibling tools like pasm_feedback and pasm_persona. An agent would need to infer these details.
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 50%: candidates has a description, agent_id does not. The description adds meaning for candidates by explaining the fallback behavior when omitted, but doesn't clarify agent_id's role or default behavior beyond the schema's 'default' field.
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 ('选一个动作' = select an action) and resource (PASM action pool), and explains the selection basis ('人格基线 + 反馈学到的偏好'). It distinguishes itself from siblings by focusing on action selection, though it doesn't explicitly name a sibling alternative.
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 implies when to use it (when PASM needs to choose an action) and gives a conditional usage note ('不传 candidates 就用智能体自己的动作池'). However, it doesn't explicitly state when NOT to use it or name alternative tools like pasm_chat or pasm_focus.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.