pasm_persona

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

With no annotations provided, the description carries the full burden. It discloses the key behavioral trait: this is a read-write tool with merge-update semantics (not replace). It also documents special interpretation of numeric persona fields (temper/energy/play as 0-1 scales) and the action pool as an array. However, it doesn't disclose whether updates are persistent, require authentication, or what the return value looks like after a view or update. A 3 is reasonable – the merge behavior is the most critical trait and is clearly stated, but other behavioral context is missing.

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 (about 40 Chinese characters) and every sentence carries information: mode selection, merge behavior, and key semantics. It is front-loaded with the purpose and immediately actionable. 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 2 optional parameters and no output schema, this description covers the core usage completely. The persona update semantics are fully explained including merge behavior and field domains. The main gap is agent_id semantics and the return value for both modes, but since the tool is likely a simple get/merge-set with a default agent, the description is sufficiently complete for an agent to invoke it correctly. A 4 is appropriate.

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%: the 'persona' parameter has a brief description, and 'agent_id' has only a default with no explanation. The description adds substantial semantics for the persona field by enumerating common keys (name/role/tone/temper/energy/play/actions) and their value types and scales. This compensates well for the low coverage. However, agent_id is still not explained in the description – an agent may wonder whether this is a user ID, a conversation ID, or what the default means – so it doesn't get a 5.

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 begins with a clear verb+resource combination: '查看或更新人格' (view or update persona). It explicitly distinguishes two modes: viewing when no persona is passed, and merging updates when one is provided. This is a specific, unambiguous purpose that clearly differentiates from sibling tools like pasm_status (which likely shows overall status) and pasm_context (context management), so an agent can tell them apart.

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 explicitly states when to use the viewing mode ('不传 persona 就是查看') versus the update mode ('传入为合并更新'). It also clarifies the merge semantics: unmentioned keys retain their original values. This is explicit when/how-to guidance, even though it doesn't name alternatives, it fully specifies the usage conditions for this tool's two modes.

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