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

Adds real behavior beyond the annotations: what gets cleaned (duplicate edges, empty sequence labels), that layout is recomputed orthogonally, that graph meaning is preserved, and that no semantic verification occurs. Slight tension with `idempotentHint: false` given the 'deterministic' claim, but that is a nuance rather than a contradiction, and the mutation/no-destruction profile is consistent with the annotations.

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 action and outputs, then the usage rule, then the limitation. The '$0 compute cost, instant, unlimited' clause is promotional but does convey a useful cost/latency expectation; otherwise there is little waste.

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?

With no output schema, the description carries the burden of stating return values and it does so explicitly. It also covers the important edge case (missing steps cannot be invented) and the auth path is handled by the schema, so an agent has everything needed to call this 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?

Schema coverage is 100%, so `spec`, `swimlane`, `orientation`, and `authToken` are already documented in the schema. The description confirms `spec` is healed and re-rendered but adds no meaning to the layout toggles or auth parameter, so baseline 3 is appropriate.

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 and resource — deterministic connector healing plus full re-render of a VisualSpec — and enumerates the concrete outputs (svg, mermaid, excalidraw, studioUrl). Against siblings like compile_workflow, enhance_workflow, and revise_workflow this is clearly a mechanical heal-and-render pass, not a semantic edit.

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 triggers: use after direct structural edits to `nodes`/`edges`, or when a user asks to autofix connectors. It also scopes out semantic work by warning that missing steps or branches require source-backed spec edits. No sibling tool is named as an alternative, which keeps it just short of a 5.

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