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

The description does not disclose any side effects, error conditions, or response format. It mentions a billing cost but omits critical behavioral details. The reference to non-existent cursor/count parameters further undermines transparency about the actual operation.

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?

The description contains extraneous metadata ('Group: User. Billing per call: 1 Credits.') that is likely available elsewhere and does not aid understanding. The cursor/count mention is irrelevant given the schema, making the description overlong and unfocused.

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?

The description fails to specify the output structure (e.g., list of like objects) or any pagination mechanism, and it contradicts the schema by referencing non-existent cursor/count. Without these details, the tool cannot be used reliably in conjunction with other tools.

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?

The only parameter, userId, is not described beyond its name. The schema provides no type info beyond string, and the description adds no context about its format, requirements, or meaning. The mention of cursor and count, which are not in the schema, adds confusion rather than clarity.

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 title 'User Likes by userId' and description 'Receive all likes of a user' clearly indicate the tool fetches likes for a specific user. It is distinct from sibling tools like get_tweet or get_user_followers, though it could be more explicit about the nature of 'likes' (e.g., tweets liked).

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 mentions using 'cursor and count to navigate around,' but these parameters are not present in the input schema (only userId is defined). This is misleading and provides no guidance on when to use this tool versus alternatives or how to handle pagination effectively.

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