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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description adds substantive context beyond them: broad follows can pull in existing unreceived history, following can start paid catch-up work within hosted-continuation limits (a cost side effect), and it explicitly grants no posting/disclosure permission. It stops short of saying what unfollowing does to already-followed history or how a stale revision is handled.

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?

The core action is front-loaded, but sentences are dense and occasionally cryptic ('This configures the setup's own attention, and another chat's acknowledgment does not acknowledge it') and there is no structural separation of scope, side effects, and permissions.

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?

An output schema exists so return values need no explanation, and annotations cover the safety profile, but for a 5-required-param mutation with a oneOf target the description omits revision-conflict behavior and the remaining parameter semantics, leaving an agent to infer call correctness from the schema alone.

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 only 20%, so the description must carry parameter meaning, yet it only explains target.level ('says which'). It leaves expected_revision (the optimistic-concurrency token implied by 'one exact setup revision'), following, and space_id's special 'commons' value unexplained, and the nested target discriminator is barely covered.

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 pair (follow/unfollow) and a specific resource (one exact setup revision, at space/channel/thread level selected by target.level). An agent can tell what it does, but it never names the sibling space_set_follow or space_list_follows, so a reader cannot distinguish 'setup follows' from 'my actor follows' without outside knowledge.

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?

It implies the calling context ('As the account owner', 'one exact setup revision') and hints at prerequisites, but it gives no explicit when-to-use/when-not and no alternatives, which is a real gap given a near-identical sibling (space_set_follow) and a discovery sibling (space_list_follows).

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