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

The description goes well beyond the annotations. While annotations already declare destructiveHint=true, the description adds critical behavioral details: deletion is irreversible, it only affects the reuse layer and not already-submitted signup forms, and includeFiles defaults to false meaning file references are only deleted when explicitly requested. It also notes the login requirement. This is exactly the kind of context an agent needs before invoking a destructive operation.

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 well-structured with clear sections: when to use, combination chain, and caveats. Every sentence earns its place. The most critical information (irreversibility, confirmation requirement) is front-loaded in the caveats section. The formatting with bold headers and numbered points makes it easy for an agent to parse.

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 destructive tool with no output schema, the description covers everything an agent needs: prerequisites (login), when to use, what it deletes, what it doesn't delete, the confirmation requirement, the includeFiles edge case, and the relationship to sibling tools. The combination chain with get_my_signup_profile is explicitly stated. Nothing critical is missing.

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 100%, so the schema already documents both parameters. The description adds value by explaining the source of the keys (from get_my_signup_profile's items[].key) and by clarifying the includeFiles semantics with a warning that it must be confirmed with the user before setting true. The description doesn't repeat the schema but enriches it with operational context.

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 clearly states the tool's purpose: when a user asks to delete stored signup answers (like WeChat ID or phone number), this tool permanently removes those rows from the cross-form reuse layer. It distinguishes itself from the alternative submit_signup's clearKeys by explicitly noting the old limitation. The verb '忘掉' (forget) plus the resource '报名资料' (signup answers) is specific and unambiguous.

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 provides explicit when-to-use guidance: '【需要登录】【何时用】用户说「把我存的微信号删掉 / 别再自动填我的手机号」时调它'. It also names the alternative (submit_signup's clearKeys) and explains why this tool is different. The combination chain with get_my_signup_profile is clearly laid out, and the caveats section explicitly states what not to do (don't delete submitted signup forms, don't delete files unless includeFiles=true).

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