Request Delta Second Reading

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

With no annotations, the description carries the full behavioral burden and does so richly: dry-run vs billed execution, 402 on insufficient balance, 409 generation_active while a build holds the model, skipped-control reasons (no_draft, read already), and outcome values (usable, unusable, failed, unavailable). This is exactly the kind of side-effect and failure disclosure an agent needs.

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?

Front-loaded with the core concept, then the dry-run/confirm split, then the refusal condition. Dense and each sentence carries information (billing, relay-to-person warning, error codes). Slightly long for the message, but nothing reads as 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 mutating, billed operation with no annotations, this covers cost, refusal conditions, skip reasoning, per-control outcomes, and the mandatory human-relay step. An output schema exists, so return values needn't be spelled out, and the description still adds useful outcome semantics.

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 75%, and the schema already documents model_id, control_ids (the 30-ID cap), and confirm_estimate. The description reinforces confirm_estimate's intent but adds no syntax or format detail beyond the schema, and server_version is undocumented in both places. Baseline 3 is appropriate given the schema does the heavy lifting.

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 gives a specific verb and resource — reading controls' text into deltas a second time — and clarifies the defining constraint ('a delta is declared only once its draft has been read twice'). It doesn't name or contrast the sibling delta tools (get_control_delta, declare_control_delta, submit_control_delta), so the agent must infer the distinction, but the operation itself is unmistakable.

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 operational guidance: without confirm_estimate nothing is charged or written and the estimate 'must be RELAYED TO THE PERSON first. Never confirm on your own.' That is a clear when/when-not rule for the confirm flag. It stops short of positioning this tool against the other delta siblings, so it is clear context without alternative comparison.

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