create_decision

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

With no annotations, the description carries the full burden and does disclose real behavior: the created record defaults to status 'suggested', expires for review after 14 days, and feeds statistics/review loops. It also documents the return payload (decision_id, review_at). It does not mention permissions, whether duplicate decisions are allowed, or failure modes.

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?

Front-loaded with the core behavior, then parameter semantics, then return values — a logical reading order. The user-phrasing bullet block is mildly redundant but does add intent-matching value; the rest is tight.

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 5-parameter mutation tool with no annotations, it covers purpose, all parameters, side effects on status/expiry, and return fields (an output schema exists so return details need not be exhaustive). Missing only edge-case guidance such as valid monitor_id preconditions or duplicate handling.

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 0% and no enum is declared, so the description does essential work: it enumerates the five valid action values, states target_price is expected for follow_price/raise_price, and explains that context_json accepts an object and will be serialized. That compensates fully for the empty schema descriptions.

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 (record a follow-sell decision, status=suggested, 14-day review), plus the downstream lifecycle. It also names adopt_decision and reject_decision as the follow-up actions, so an agent can separate creation from adoption/rejection without opening other schemas.

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 example user utterances ("记一下我的决定：跟着降到 199") map natural-language intents to this tool, which is unusually actionable guidance. It also describes the workflow continuation via adopt_decision/reject_decision, but never states when NOT to use it (e.g., versus review_decision or when a decision already exists).

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