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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false). The description goes well beyond that: the draft opens in Workbench's simple editor at a concrete path, may return needs_confirmation requiring user approval and re-call with approvalId, and opportunityId is refused when the change already has a draft. Rich behavioral disclosure the annotations cannot supply.

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 then structured as author-guide → return-path → follow-on tools. Dense and long for a single description, but nearly every clause is actionable and nothing reads as filler.

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 12-parameter mutation tool with no output schema, the description covers the critical operational context: what gets produced, where it opens, the approval loop, the linking behavior, and the recommended next tools. An agent has enough to call it correctly on the first attempt.

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, but the description adds meaning on top: it explains how to choose `mode` (pattern → use case), calls for [STUB: ...] markers paired with stubNotes, and describes the flow↔change linking role of opportunityId. It adds value beyond the schema, though it does not touch every parameter.

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 ('Creates a runnable first-draft flow from a spec you author') and frames the scope as scaffolding a draft rather than editing, running, or publishing one. An agent can distinguish it from siblings like workbench_flows_update, workbench_flows_fork, and workbench_flows_run without opening any schema.

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 pattern-selection guidance (classifier for read-and-bucket, structurer for transform/extract, agent for conversational) and names the follow-on tools with their conditions: workbench_flows_run to try it, workbench_flows_publish when ready for schedules/share links. It also covers the needs_confirmation edge case and the Compass opportunityId path.

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