Like or unlike a comment

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

Adds genuinely non-obvious behavior beyond the annotations: the TikTok 'comments' capability requirement, where to verify it (`capabilities` in list_users), and the operational consequence that older connections must reconnect. This is exactly the auth/prerequisite context annotations don't convey.

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 carrying distinct information (action + inverse, platform scope, prerequisite). The primary action is front-loaded and the caveat follows, with no filler.

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?

With an output schema present and full schema coverage, the description needn't explain return values, and the platform/auth constraints are covered. It could note failure behavior for unsupported platforms, but nothing essential for a correct call is missing.

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%, so the baseline is 3, but the description adds meaning: the action is performed 'as the profile's account', clarifying the `user` parameter's semantics, and it reinforces the boolean toggle's dual meaning. No syntax or format gaps remain.

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 ('Like a comment as the profile's account') plus the inverse operation via `liked: false`, and scopes it to TikTok and Facebook. It does not differentiate from the ambiguous sibling `comment_action`, which likely overlaps, so an agent can't fully rule out alternatives from the description alone.

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?

Gives clear conditional guidance: use the default to like, pass `liked: false` to remove the like, and platform is limited to TikTok/Facebook. It also states a prerequisite. It stops short of naming an alternative tool for cases where this one doesn't apply.

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