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

Goes well past the generic destructiveHint/openWorldHint annotations: it discloses that consent changes fence the old revision and trigger Task cancellation, that broad follows may make unreceived history eligible for budgeted catch-up charges, and that discussion text cannot grant spending or disclosure. Those are exactly the non-obvious side effects of a destructive, open-world write.

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?

Information-dense with no filler sentences, but it is one undifferentiated block that opens on a scope restriction rather than the action, and mixes purpose, prerequisites, and side effects without structure. Bullets or an action-first lead sentence would have made this significantly easier to parse.

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 12-parameter, nested, destructive tool, the description covers the highest-risk behaviors (cancellation on consent change, catch-up spend, disclosure limits) and an output schema exists to cover return values. The main residual gap is the create/update payload semantics, which are pushed entirely to the schema.

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?

With 17% schema description coverage the description should compensate more than it does; it maps the enable-required fields in prose ('accepted rate card, per-Task maximum, aggregate accepted-commitment limit and expiry'), but leaves setup_id, expected_revision, name, agent, and the whole nested configuration object unexplained. Most of the real param documentation lives in the schema's own top-level and per-property descriptions, so prose adds only partial value.

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 states a specific verb set and resource ('create or update an internal agent setup, or explicitly enable/disable its hosted continuation on followed Spaces') and names the sibling it is not ('use product_get_started'). It does not distinguish itself from agent_delete, agent_set_follow, or agent_grant_set, and the 'O++' / 'internal agent' jargon adds ambiguity for a first-time agent.

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?

Explicitly routes agents away from setup/connection to product_get_started, and states the prerequisites for the enable path (accepted rate card, per-Task max, aggregate commitment limit, expiry). However it gives no exclusion guidance against update vs enable vs disable beyond what the schema's own action-description already carries.

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