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

Annotations only declare the mutation/destructive/open-world profile; the description goes well beyond them by disclosing consequence semantics: new thread follows start at the current reply count, broader follows may trigger hosted catch-up that reads existing history, thread unfollow is overridden by a covering channel/Space, and following grants no membership or posting rights. It also states the auth prerequisite ('sign-in or a linked agent') and is consistent with destructiveHint=true since unfollowing has non-obvious effects.

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 with the core verb/resource and discriminator, followed by one sentence per meaningful consequence. Five dense sentences, each carrying a distinct behavioral fact with no repeated schema content or 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?

For a destructive, multi-level mutation with an output schema already covering return values, this description covers what an agent needs before calling: level selection, follow/unfollow consequences, catch-up side effects, mute interplay, permission boundaries, and auth requirements.

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 only 33%, so the description must compensate, and it does for the two most semantically loaded inputs: target.level selection and the effects of the boolean 'following' value. space_id is left entirely to the schema's short pattern note, so compensation is real but not complete.

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 first sentence names a specific verb pair and resource ('Follow or unfollow a Space, channel or thread') and immediately explains the discriminator ('target.level says which'). An agent can distinguish this from siblings like space_list_follows or space_mark_thread_seen without opening any schema.

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 gives useful behavioral conditions for using follow vs unfollow at each level ('following again keeps received-message receipts', 'Unfollowing a thread does not mute it'), which implies when each choice applies. However, it never routes the agent to a specific alternative sibling (e.g. space_list_follows for inspection, space_mark_thread_seen for read state) and states no explicit when-not-this-tool rule.

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