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

No annotations exist, so the description carries the full behavioral burden, and it does disclose key traits: nothing is persisted, it consumes one builder_call credit, and it returns {reply, proposal, changes} with the placeholder pipeline_id convention. However it does not say whether the call is idempotent, whether history is truncated, or what happens on invalid workflow_id, so the disclosure is substantial but not complete.

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?

Purpose is front-loaded in the first clause, then return shape, then the apply procedure, then parameter notes and the cost caveat. It is telegraphic and dense but every sentence carries operational information; the compressed notation ("new:<key>", "{reply, proposal, changes}") trades a little readability for brevity.

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 and zero schema description coverage, the description supplies both the return structure and the field-level meaning of proposal (name, graph, task_variables, cron_expr, new_pipelines, needs, plan). Combined with the cost note and the apply workflow, an agent has everything needed to call it and act on the result.

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 description coverage is 0%, so the description must compensate and largely does: workflow_id = the existing workflow to change, history = earlier [{role, content}] turns, start = manual|schedule|webhook, and the placeholder "new:<key>" convention is explained in the proposal context. Only "message" is left implicit via "Ask the ... assistant", keeping it just short of a 5.

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 ("design a new workflow or change an existing one") and immediately distinguishes itself from the mutating siblings by declaring "NOTHING is saved". An agent can tell this is a proposal/drafting endpoint rather than a persistence call 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?

Explicitly scopes usage to design-new or modify-existing (via workflow_id) and then lays out the exact downstream sequence: create new pipelines with workflow_builder_create_pipeline, substitute "new:<key>" with real ids, then workflow_create / workflow_update. That is an explicit when-to-use plus named alternatives and their ordering, leaving little to inference.

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