Commit workflow

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

Goes well beyond the annotations (readOnly=false, idempotent=true, destructive=false) by disclosing atomicity of the write, the semantics of approval attestations (they bind reviewed inputs but do not prove a human reviewed them), and the no-substitution/fresh-preview rule. This is exactly the mutation context 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?

Dense but front-loaded, leading with the core action before the gating rules and recovery guidance. Every sentence carries load, though the attestation aside and recovery clause make it longer than strictly minimal.

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?

No output schema exists, and the description doesn't need to explain return values, but for an atomic commit tool it covers inputs, preconditions, and failure recovery thoroughly. A brief note on what a successful commit produces would close the remaining gap.

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 only 33% and the approval object is nested, yet the description adds real meaning: preview_id alone is insufficient, confirmed must be true, and preview_hash must equal the hash of the exact preview the human reviewed. It does not cover farm_id (left to the schema) and gives no format example for the hash beyond the schema pattern.

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+resource ('Save one approved workflow preview') and names the mechanism ('atomic birth writer'), and implicitly distinguishes itself from preview_workflow/get_workflow_preview by insisting on approval + preview_hash rather than a preview id. It never explicitly names a sibling as the alternative operation, so it stops short of a 5.

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?

Explicit preconditions (approval.confirmed true and the exact reviewed preview_hash; a bare preview id is insufficient), an exclusion ('accepts no replacement inputs; a changed payload or relevant state requires a fresh preview'), and a recovery alternative ('read get_workflow_preview first'). When/when-not/alternative routing is all present.

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