confirm_write

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

Annotations already indicate destructive and non-idempotent behavior, but the description adds valuable detail: the exact XML is sent unchanged, and a previewId can only be confirmed once, with reuse failing rather than silently reposting. This meaningfully exceeds annotation-only information and matches the destructive hint.

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?

Three focused sentences with no filler. The core purpose and exclusive write behavior are front-loaded, followed by the parameter source and the one-time-use constraint.

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 single-parameter confirmation tool with annotations covering safety, the description covers the workflow, source of the ID, exclusivity of the write, and failure behavior on reuse. Nothing critical is missing for an agent to call it correctly.

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?

The schema already documents previewId as returned by preview_write, so the baseline is 3. The description adds context that this ID ties to a previously-built preview and that the exact XML is transmitted unchanged, reinforcing the parameter's significance beyond a simple string field.

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 action (post a preview), a resource (Tally), and the exact workflow stage (after preview_write). It explicitly distinguishes itself as the only tool that actually writes for previewed batches, so an agent can clearly separate it from preview_write and the many create/update siblings.

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 when-to-use rule: after preview_write, using the returned previewId. It also names preview_write as the required precursor and notes that reuse of confirmed/expired IDs fails, marking the boundary of the operation.

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