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

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description adds genuinely new context: no execution, approval enforcement, credentials prohibited, and a prompt-injection warning that provider record text is untrusted. That is substantial beyond annotations, though it says nothing about what the saved plan looks like on failure or limits on the durable record.

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-loads the core action and the 'does not execute' constraint in the first two clauses, then layers safety and platform context. Dense but every sentence carries information an agent needs.

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?

Output schema exists so return values need not be described, and the description supplies the safety, approval, and documentation pointers an agent needs. Minor incompleteness remains around the unmentioned parameters and the shape/size limits of a saved workflow.

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 carry parameter meaning, and it partially does: it explains endpointId, ordinary request input, earlier-step dependencies, and gives a concrete binding example ({target:'pathParameters.id',...}). However 'name' and the behaviorally important stopOnError toggle are never explained, leaving real gaps.

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 ('Save a durable exact multi-step workflow for review') and immediately bounds scope with 'Does not execute', which cleanly separates it from system_execute_write and system_control_workflow. An agent can distinguish planning from execution without opening the 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 an explicit entry condition ('Start only if user requested execution') and notes that per-action approvals remain enforced, plus guidance that steps must use discovered endpoint IDs and real successful results. It does not nail down when to prefer system_control_workflow or system_workflow_status over this tool, so routing between the workflow siblings is still partly inferred.

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