Plan actions

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

With no annotations, the description carries the full behavioral burden. It clearly discloses the most important safety behavior: nothing executes until approve. It also describes previews and that raw args remain available. It does not mention auth or failure modes, but the key non-mutating guarantee is well covered.

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?

Two sentences with no filler. The core transformation and the critical non-execution guarantee are front-loaded, and preview details are compactly summarized.

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 tool with a nested actions schema and no output schema, the description covers the essential behavior and output characteristics. It could say more about the exact returned plan structure or payment/auth expectations, but the current description gives an agent enough to call it correctly in the approve workflow.

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 0%, so the description must compensate. It adds meaning to the `actions` parameter by framing them as 'intended writes' and explaining what per-action treatment they receive. It does not fully narrate the object shape, but the schema already provides structure and the tool enum, and the description supplies the functional semantics.

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 uses a specific verb ('Turns intended writes into an ordered plan') plus a clear resource and scope. It also names what the output includes (per-action previews) and the non-execution behavior, making the tool's role clearly distinguishable from siblings like approve and dry_run.

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?

The description provides clear usage context: it is for intended writes before approval, and 'Nothing executes until approve' implies a sequencing constraint. It does not explicitly name alternatives or when not to use it, but the workflow implication is strong enough for an agent to infer correct invocation timing.

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