vro_save_workflow

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

With no annotations, the description carries the full burden and does well: it discloses side effects (builds schema, creates missing folder path, validates), an ES5 scripting constraint, control-flow defaults (array order unless next/ifTrue/ifFalse), and a versioning policy (new = 1.0.0, patch bump on update unless version/bump given). It omits auth/permission needs and what happens on validation failure or when overwriting an existing workflow.

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: the upsert purpose and spec come first, then side effects, then the scripting constraint, versioning, and dryRun. Sentences are information-bearing, though the version-bump rule is stated twice (in prose and implied again in the schema) and the block is on the long side.

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 10-parameter nested-spec tool with no output schema and no annotations, the description covers the authoring model, control flow, versioning, and dryRun preview well enough to call it correctly. Remaining gaps are return-shape specifics (workflow id, resulting version, validation errors) and permission requirements, which are not addressed.

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 30% across 10 parameters, so the description must compensate, and it does for the highest-value ones: dryRun's preview-only XML behavior, the version/bump interaction, step ordering and next/ifTrue/ifFalse routing, and the inputs/outputs/attributes spec. It adds real meaning beyond the schema, though args/action linking and resultTo are left entirely to the schema.

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 (upsert/create-or-update) and resource (Orchestrator workflow) plus the keying rule (name + folder) and the spec it consumes. It is distinguishable from sibling save/find tools like vro_save_action and vro_get_workflow 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?

The create-vs-update behavior is implied by 'upsert by name + folder' and dryRun gives a preview path, but there is no explicit when-to-use guidance, no prerequisites (e.g. whether an existing workflow should be fetched first), and no named alternatives such as vro_save_action. Usage is inferable rather than stated.

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