confirm_write

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

With no annotations, the description carries the full burden and does so well: it discloses the authorization source (BULLHORN_MCP_ACTOR), idempotency semantics (preview must not be expired or already used), staleness protection (hash match and unchanged content), and the refusal path with an example error code. The enumerated result statuses (partially_committed, failed_orphan) also hint at non-atomic failure modes an agent must handle.

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?

Well front-loaded: purpose in the first sentence, then gating conditions, then args and returns. The Returns block partly restates what the output schema already provides, which is the only mildly expendable content.

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?

An output schema exists so return values need not be spelled out, yet the description still summarizes the status vocabulary. Combined with prerequisites, actor provenance, and failure modes, nothing material is missing for correctly invoking a confirmation/commit tool.

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, and it does: it explains that operation_id and preview_hash come from the preview response, and it supplies the accepted decision values ('approve'/'reject') that the schema itself leaves as an unconstrained string. All three parameters gain meaning beyond the bare typed properties.

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?

Names a specific action pair (approve/reject) on a precisely scoped resource ('a previewed write'), which no sibling tool claims. An agent immediately understands this is the confirmation step of a preview-then-commit flow, not a direct write tool.

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 makes the prerequisite flow clear: the operation_id and preview_hash must have been produced by a prior preview, and it enumerates the exact gate conditions under which the write proceeds. It stops short of naming the preview tool explicitly or stating what to do when the preview is missing, so it falls just under fully explicit routing guidance.

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