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

Goes well beyond the annotations: discloses that the author sees the liker's identity, that only the first like fires an interaction notification, that repeat likes are silent (idempotent), that consent is required, and that unliking affects only the caller. These are non-obvious social side effects an agent must know before acting.

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?

Two tight bracketed blocks, front-loaded with the login requirement, then the toggle semantics, then the pitfalls. Every clause (idempotency, notification fan-out, consent, unlike scope) carries actionable weight.

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 two-parameter mutation with no output schema, the description covers auth, idempotency, notification behavior, and consent obligations, leaving nothing the agent needs to call it safely. No return-value documentation is required.

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% and the schema already documents both momentId and the like boolean with default. The description restates the like=true/false toggle but adds no syntax, format, or id-sourcing detail beyond the schema. Baseline 3 applies.

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?

States a specific verb and resource (给一条消息圈点赞) and immediately clarifies the bidirectional semantics (like 缺省 true / like=false 取消赞), so an agent can distinguish it from comment_moment or publish_moment 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?

Provides concrete preconditions: 需要登录 and 点赞前要用户同意 (obtain user consent before liking) – a real when-to-use constraint. It does not explicitly name alternative sibling tools, so it stops short of a 5.

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