Follow post

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

Adds real context beyond annotations: scope is limited to the caller's own notifications, the effect is reversible via following=false, and it is safe to run without confirmation. That directly supplements destructiveHint=false and idempotentHint=true rather than repeating them. It does not cover failure modes (e.g. following a post in a group you cannot access).

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 sentences, front-loaded with the outcome, then mechanics, then the safety note. Every sentence carries information an agent would otherwise have to guess.

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 toggle with a full schema and no output schema, everything needed to call correctly is present: what changes, what the boolean does, the default, the own-post caveat, and that no approval 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 coverage is 100%, so baseline is 3; the description still adds meaning by spelling out that 'following false unfollows' and by clarifying the own-post edge case that no parameter expresses. The mapping of post_id to list_posts stays in the schema, which is fine.

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?

Opens with a specific verb and outcome ('Get notified of new comments on a post, or stop') and names the exact resource (post). It distinguishes the tool from adjacent post operations like comment_on_post or set_post_comments by framing it as a notification subscription toggle.

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?

Explicitly states when to use it (wanting new-comment notifications) and how to undo (following false). It also pre-empts a common mistake by noting you already follow your own posts from the start. It stops short of naming a sibling alternative for notification management (e.g. list_notifications), so not a full 5.

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