direct_apply_changes

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

Annotations already declare the write/idempotent/destructive/openWorld profile, but the description adds real value beyond them: 'exactly once', a re-read verification step, that it 'spends units', and that it fails closed without approval. The only gap is that cost magnitude and rollback behavior on partial failure are not described.

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?

A single dense sentence followed by two short constraints; the trigger, key parameters, and failure mode are all front-loaded with no filler. Every clause carries information.

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, idempotent write with an output schema (so return values need no explanation), the description covers trigger, gating, cost, and verification. The unexplained `service`/`method` params keep it from being fully self-sufficient.

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 0%, so the description must carry parameter meaning, and it only partly does: it tells the agent that approval_id gates the operation and idempotency_key enforces exactly-once, and hints 're-reads campaigns' relates to campaigns. The required `service` and `method` parameters are left entirely unexplained.

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 (Apply) and resource (an accepted Direct change set) and explicitly names the upstream producer, `direct_prepare_changes`. This cleanly separates it from its prepare sibling and from the generic `direct_write`/`direct_apply_write` group.

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 clear trigger context: the change set must come from `direct_prepare_changes` and be operator-approved, and 'Fails closed without approval' states a refusal condition. It does not, however, differentiate itself from the sibling `direct_apply_write`, so a routing agent still has an ambiguity to resolve.

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