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

Annotations only declare idempotentHint=true and destructiveHint=false; the description adds real value beyond that with an auth requirement (organizer/login), explicit non-effects (no phone numbers fetched, no send records created), and the fact that the draft is not a delivery. The one weak spot is the vague '可用AI', which hints at optional AI generation without saying how it is triggered given there is no AI-related parameter.

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?

Extremely dense and front-loaded with the permission scope, and every clause (permission, input source, side-effect exclusions, delivery semantics) carries distinct information. The telegraphic semicolon style is efficient, though it reads as shorthand rather than fully formed guidance.

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?

Permissions, side effects, and the draft-vs-send distinction are covered, which is the hard part for a mutation tool with an idempotent/non-destructive annotation profile. However, for a 4-parameter tool with no output schema and zero parameter documentation, the unexplained `tone` enum and `body` semantics leave meaningful gaps.

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 4 parameters, so the description must carry the burden and mostly does not: it names userIds and its source, but says nothing about `body` (1200-char limit, whether it is generated or required), the `tone` enum (warm/concise) and its default, or the 1-50 item bound on userIds.

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+resource pair (draft guest SMS body for an activity) and immediately bounds it with '不取电话、不建发送记录' and '草稿非送达', which cleanly separates it from siblings like send_guest_invite_now and get_activity_guest_sms. An agent can identify the operation and its scope without opening the schema.

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?

It states the prerequisite ('登录/主办方'), the correct upstream source for inputs ('userIds取get_activity_guest_sms'), and where the actual sending happens ('本人App编辑发送'), so the agent knows the workflow position. It does not explicitly say when to choose this over send_guest_invite_now, but the '草稿非送达' contrast makes the boundary inferable.

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