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

Adds substantial context beyond the readOnly/openWorld/non-destructive annotations: the counterintuitive pagination behavior (a page can be empty while has_more is true, continue with next_cursor), the meaning of following:false as a receipt, the extra fields on thread entries, and the auth requirement (sign-in or linked agent). These are exactly the traits that would otherwise cause an agent to misread results or stop paging early.

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?

Dense but front-loaded: the core action lands in the first clause and each following sentence conveys a distinct operational fact. The phrase about shared receipt state and retaining actual cursors is the one sentence whose meaning is hard to parse on first read.

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, return values needn't be spelled out, yet the description still flags the thread-specific fields and the unread-count asymmetry. Combined with pagination and auth guidance, an agent has what it needs to call and interpret it; only the cryptic cursor-retention caveat leaves residual ambiguity.

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 75% and already documents view, cursor, and space_id, but the description adds semantics the schema lacks: what following:false means, which fields appear on thread entries, that broader targets have no unread count, and the empty-page/has_more interaction with cursor. Only limit/default paging semantics remain untended, which is minor.

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+resource ("List what you follow") and immediately qualifies scope with the view enum and the receipt-vs-subscription distinction. It does not explicitly contrast with the nearest sibling, space_list_threads (which lists threads in a space rather than followed threads), so an agent must infer the boundary.

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 concrete selection rules: use view:"threads" for active thread follows only, omit space_id to cover Community Spaces, supply space_id for a private Space. It also rules out a misuse case ("This is not an activity feed"). Missing only an explicit named alternative for related listing tools.

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