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

Annotations already declare destructive, idempotent, open-world and non-read-only, but the description adds substantial context beyond them: the async result state `created_pending_processing`, that the target may look empty for minutes, that the sync keeps running (and survives revocation of this assistant's access), the request_id idempotency contract including the failure mode on mismatched params, atomic all-or-nothing creation for two-way, and zero credit cost.

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 and its precondition are front-loaded, and paragraphs are thematically split (confirmation, idempotency, result lifecycle, two-way rules, out-of-scope). It is dense and somewhat long, but nearly every sentence carries operational information rather than 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 mutation tool with 6 parameters, an output schema, and a genuinely complex lifecycle (preview dependency, background processing, persistent sync semantics, two-way atomicity), the description covers confirmation requirements, return-state expectations, retry behavior and limits. Nothing an agent needs to call this correctly is missing.

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 100%, so baseline is 3, but the description adds real semantics: request_id stability rules, default direction, reverse_detail_level defaulting to detail_level in two-way, and the constraint that detail levels must not exceed max_detail_level/max_reverse_detail_level from preview_sync.

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 and resource ('Creates a sync between two of the user's own calendars') and immediately narrows scope to the user's own calendars, one-way or two-way. It also delineates what this tool does NOT cover (syncs with other people, changing rules, reversing direction) and names the alternative surface for those.

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?

Gives an explicit precondition ('after the user confirmed this specific source, target, direction and detail level(s) in the chat'), a required prior step ('Call preview_sync first and tell the user what it reports'), and routes deletion and out-of-scope sync management to named siblings (preview_delete_sync, delete_sync) and the Kalender Sync app via syncs_url.

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