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

Annotations already cover the read-only, non-destructive, closed-world profile, so the description earns credit for adding ordering semantics ('stable follow-ID order'), pagination contract ('continue while has_more is true'), and shape differences ('broad targets have no aggregate unread count; thread receipts include opening_seen and reply_cursor'). The closing caveat about shared receipt state is opaque but signals a real semantic limit.

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?

Front-loaded and compact, but several sentences are cryptic rather than concise — 'Shared receipt state does not establish this task's actual received sequence' costs a sentence and conveys little actionable meaning. The field-level detail is good; the negative framing is padded.

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?

Output schema exists, so return values need not be explained, and the description usefully covers ordering, pagination, and the thread-receipt fields. What is missing is any explanation of the required space_id scope and the limit parameter, which an agent needs before it can call this 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 description coverage is 0% across three parameters, so the description must compensate and does not: space_id, limit, and cursor (including the f_ prefixed pattern) are never explained. Only the has_more/cursor continuation behavior is hinted at, leaving required-parameter meaning and the 1-50 limit range undocumented.

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 ('enumerate') and resources ('Space, channel and thread follow targets' plus thread receipts), with an ordering guarantee. The explicit 'This is not an activity feed' line separates it from feed-like siblings, though it never names private_space_list_followed_threads or private_space_set_follow as the natural complements.

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?

'This is not an activity feed' and 'Continue while has_more is true' give implicit routing and pagination guidance. But no sibling is named as the alternative for the excluded use case, and the description never says when an agent should call this rather than private_space_list_followed_threads or private_space_get.

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