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

Annotations only say destructive and not read-only; the description goes well beyond by disclosing that broad follows make unreceived history eligible for budgeted catch-up charges, that changing consent fences the old revision and requests Task cancellation, that the caller should inspect cancellation_requested and the retained Task ID, and that discussion text cannot grant spending or disclosure. These are exactly the side effects an agent must weigh before mutating a subscription.

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?

Five dense sentences, front-loaded with the verb/resource and actor, then escalating to billing and cancellation consequences. Nothing is padded, though the telegraphic phrasing ('Changing consent fences the old revision') trades a little readability for density.

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 four-variant oneOf schema with a destructive annotation and an output schema, the description covers every action's requirements and the important side effects (chargeable catch-up, cancellation, consent revisioning). Remaining gaps are minor: retry/idempotency expectations and what to do on a revision mismatch are left implicit.

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 high, so structured data already documents most fields; the description still adds meaning by enumerating the four inputs enable requires and by explaining the revision-fencing implication of expected_revision. It does not clarify idempotency_key behavior or how expected_revision conflicts surface, so it stops short of full compensation.

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 description names four concrete verbs (create, update, enable, disable) bound to a specific resource (an internal agent setup / its Space subscription) and states the actor constraint (account owner). This separates it cleanly from siblings such as private_agent_setup_follow, private_agent_setup_list and private_agent_setup_remove.

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 gives explicit preconditions for the privileged path ('As the account owner' and the four required enable inputs: rate card, per-Task maximum, aggregate commitment limit, expiry), so an agent knows an enable call is not free-form. It does not, however, route the agent to sibling tools (follow/list/remove) or say when a plain update should be preferred over disable-then-create.

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