Execute a verified multi-tool AI workflow

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

Annotations declare destructive/mutating, but the description adds critical behavior: mutations are blocked by default, mutating steps are never retried unless retryMutations=true, maxSteps caps the run, stopOnError defaults true, and it requires explicit-mutation-approval. This is well beyond what the structured fields provide.

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?

The lead sentence is strongly front-loaded, but the body is dense and includes a Signature block that duplicates the 100%-covered input schema, plus a metadata tail (Phase, cost, idempotency, Produces, Verify with) that is more inventory than guidance. Several sentences are load-bearing, but the piece is longer than needed.

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 high-complexity orchestration tool with no output schema, the description covers execution model, gating, retries, references, and failure recovery ('inspect tool-schema for exact fields'), and names produced artifacts (operation-receipt, step results, verification results). Nested step verification semantics are only lightly addressed but the picture is largely complete.

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 100%, so the baseline is 3, and the description adds the `$steps.stepId.data.field` / `$result.stepId.data.field` reference syntax and reiterates default gating behavior (dryRun, allowMutations, retryMutations) in prose. The embedded Signature block largely restates the schema rather than adding new 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?

States a specific verb+resource ('ORCHESTRATES LIVE TOOLS', 'Execute an explicit discover→act→verify workflow') and frames itself as 'the main closed-loop execution surface for AI agents.' It distinguishes itself from nearby siblings like execute, batch-execute, tool-plan, and agent-context by positioning them as prerequisites or components.

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 explicit when-to-use guidance ('Use `agent-context` and `tool-plan` first when the goal is vague, then pass concrete `steps`'), plus exclusions ('set allowMutations=true only when the user authorized state changes') and a fallback behavior when `steps` is omitted. The alternative routing is named, not implied.

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