点赞 / 取消点赞

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

Annotations already declare readOnly=false, destructive=true, idempotent=false, openWorld=true, so the safety profile is partly covered. The description still adds real value the annotations cannot: a dry-run-by-default two-step commit protocol (confirm=true) and a reversibility claim. The word 可逆 sits in tension with destructiveHint=true, which tempers the score but is not a flat polarity flip.

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?

Three short front-loaded clauses: action first, then the safety workflow, then reversibility. Nothing is padded, though the terse final claim 可逆 does little work and slightly conflicts with the destructive annotation.

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 3-parameter mutation tool with no output schema, the description covers the action, the confirm gate, and reversibility — enough to call it correctly. It does not mention what the preview mode returns or the auth prerequisite, which a preview/commit tool would ideally state.

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%: like (true=点赞/false=取消), video (BV/av/link formats) and confirm (must be true to execute) are all fully documented in the schema. The description restates the confirm semantics for emphasis but adds no format, default, or edge-case detail beyond what the schema already provides, so 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?

The description names a specific verb+resource pair (点赞/取消点赞视频), so an agent immediately knows this toggles a like on a video rather than adding a coin or favorite. It stops short of explicitly differentiating itself from siblings like coin_video or favorite_video, which are the most confusable alternatives.

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 gives workflow guidance — default is preview-only, confirm=true actually sends the request — which helps the agent pick the right call pattern. But it never says when to choose this tool over coin_video/favorite_video, nor warns that it requires authentication first, so usage context is only implied.

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