万忆过程存档

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

With no annotations provided, this description carries the burden, and it does disclose important side effects: failures automatically become mistake-book entries, successful conclusions automatically become experience-library entries, and an anchor_state enables breakpoint recovery. It does not mention idempotency, overwrite behavior, or authorization requirements, but the core behavioral profile is transparent.

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 one information-dense sentence with every clause doing work: scope, phase values, automatic side effects, and anchor capability. It could be lightly restructured for readability, but it contains no filler and leads with the core purpose.

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 6 parameters and a nested anchor_state object, the description covers the key behavioral contracts: what gets stored, how outcomes are classified, and why anchor_state exists. It does not explain what the call returns, whether process_id creates vs continues a trace, or the exact structure of anchor_state, but the combination with the detailed schema is sufficient for correct invocation.

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%, so the baseline is 3, but the description adds useful semantics beyond the schema: it enumerates the five phase values, explains what outcome=failure does automatically, and gives purpose to anchor_state (断点恢复). This extra context helps the agent choose correct values even though the schema already describes them.

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 the exact operation — store one phase (planning/attempt/error-correction/reflection/conclusion) of a task execution into a trajectory archive — and distinguishes this from sibling tools by noting automatic precipitation into the mistake book and experience library. It names the resource (轨迹档案) and the scope (task execution phases), so an agent can identify it immediately.

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 makes clear it is for recording intermediate execution phases and that failures/successful conclusions are auto-routed to 万忆错题本 and 万忆经验库, which tells the agent when this tool is the right choice. It does not explicitly state exclusions or name an alternative for querying/replaying traces, so it misses the top bar for explicit when-not guidance.

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