ACTION_SEND_NOTIFICATION

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

With no annotations, the description carries the full disclosure burden, and it does add real context: the host App must be registered, Android 13+ needs POST_NOTIFICATIONS, and no output variables are written. However, the two interpolation statements ('title / message 不做 ${var} 插值' vs '字符串参数支持 ${var} 插值') and the '不写任何输出变量' vs '结果以变量快照 JSON 返回' pairing read as internal contradictions, leaving the agent unsure which parameters interpolate and whether anything is emitted.

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?

Short, but poorly ordered: the permission note is buried in a parenthetical, there is a stray double period ('。。'), and the interpolation statements are split across the beginning and end of the description, which produces the contradiction rather than a coherent rule. Content is not padded, but structure undercuts clarity.

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 action with no annotations and no output schema, the description covers the important unknowns: platform permission requirement, verbatim rendering, no output variables, and the snapshot return form. The remaining gap is the ambiguity in the interpolation and output-variable statements rather than missing subject matter.

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 would be 3, but the description adds genuine semantics the schema does not: title and message are rendered verbatim with no ${var} interpolation. It says nothing extra about require, on_error, or node_timeout_ms, which are covered by their own 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 opens with a specific verb+resource: 发一条系统通知 (send a system notification), which is unambiguous about what the tool does. It does not distinguish itself from nearby siblings such as ACTION_TOAST, ACTION_LOG, or ACTION_READ_NOTIFICATIONS, so an agent must infer the boundary itself.

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?

Usage is only implied by the nature of the action; there is no explicit 'use this when…' statement and no mention of when to prefer ACTION_TOAST or ACTION_LOG instead. The Android 13+ POST_NOTIFICATIONS prerequisite is a useful precondition but is not usage routing.

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