twitter_user_likes

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

The description adds value beyond annotations by detailing return content ('each liked tweet with author and metrics, plus a pagination cursor'), ordering, and the behavioral quirk of returning empty if likes are hidden. Annotations already indicate readOnly, and description does not contradict them.

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 sentences, each with a distinct role: purpose, return details, and usage guidance. No redundant phrases; information is front-loaded.

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?

Despite lacking an output schema, the description sufficiently explains what is returned (tweets with author and metrics, cursor) and covers edge cases (hidden likes) and prerequisites. No additional information is needed for an agent to use this tool correctly.

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%, and the description adds useful context: for 'count', it mentions the endpoint default; for 'cursor', it explains pagination; for 'user_id', it reinforces that numeric ID is required and directs to twitter_user_info for resolution.

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 verb 'Get', the resource 'tweets a user has liked', and specifies ordering 'most recent first'. It distinguishes itself from sibling tools like twitter_user_tweets by focusing on likes.

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 ('infer interests or find content a user has endorsed') and a prerequisite ('Requires the numeric user_id; resolve a handle first with twitter_user_info'). It also notes the case where the account hides its likes.

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