intervene

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

With no annotations, the description carries the full burden. It does disclose the key behavioral trait — that intervention can either support or oppose the target's drive — which is genuinely useful framing. However it says nothing about reversibility, persistence of the change, or what actually gets mutated, leaving substantial behavioral gaps.

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?

A single front-loaded sentence with the verb first and two balanced clauses, no filler or redundancy. Its brevity is efficient, though it comes at the cost of the behavioral and parameter detail noted above.

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?

This is a state-mutating tool with no annotations and no output schema, so the description is the sole source of behavioral information. It omits what state is mutated, how the two directions map onto the given parameters, magnitude semantics for amount, and whether effects are reversible — too thin for a mutation tool at this complexity.

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 67%: text and amount carry descriptions, drive relies on a self-explanatory enum. The critical problem is that the description introduces a direction concept (顺/逆) for which no parameter exists — amount is a plain number and text is loosely '干预描述' — so the agent must guess whether direction is encoded via amount sign, text, or something else.

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 concrete action (人工干预) and qualifies it with two operational modes — 顺驱力 (reinforce the target's own drive) and 逆驱力 (push against its will) — which lets an agent grasp what the tool actually does. It never references any sibling tool (satisfy, event, tick), so differentiation is left to inference, capping it at 4.

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 parenthetical explains what each mode means, which implicitly helps an agent pick a direction, but there is no explicit when-to-use guidance, no prerequisites, and no mention of how this differs from satisfy or event for the same drive. Usage is implied rather than stated.

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