mkt_optimize

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

With no annotations provided, the description carries the full burden, and it does so well for safety: it declares read-only behavior, states requires_human=true, and explicitly rules out automatic budget changes and replays. What is missing is any statement about output shape or what '回执模式' (receipt mode) concretely means, so the behavior contract is strong on risk but thin on results.

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 compact sentence pair with the safety posture front-loaded and zero filler. It is efficient, though its density and the mixed Chinese/English 'requires_human=true' token make it slightly harder to parse than necessary.

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?

There is no output schema and no annotations, so the description must cover both behavior and results; it covers safety well but leaves all three parameters unexplained and never says what a suggestion response looks like. For a zero-required-parameter advisory tool it is minimally adequate rather than complete.

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 description coverage is 0% across three parameters (channel, campaign, minimum_confirmed), so the description must compensate but largely does not. '按记分卡与回执模式' faintly hints that a confirmation threshold relates to receipts, but channel, campaign, and the default of 3 for minimum_confirmed get no clarification at all.

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 says it produces read-only optimization suggestions and proposes next steps '按记分卡与回执模式' (per scorecard and receipt patterns), which identifies the output type (suggestions) but never states the object being optimized — campaigns, channels, or budgets — beyond saying budgets are not changed automatically. Against 42 siblings including mkt_scorecard, mkt_plan_lint, mkt_revise and mkt_action, no sibling is named or excluded, so the agent cannot cleanly tell it 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 phrase '按记分卡与回执模式' implies a usage context (invoke once scorecard results and receipts exist), but this is only implied. There is no explicit when-to-use, no when-not, no prerequisite statement, and no routing to alternatives such as mkt_revise or mkt_action, which is a significant gap in a 42-tool family.

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