Start a Flow: plan a goal (nothing is created)

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

Goes well beyond the annotations: it declares that nothing is created or sent, only a Flow with status 'proposed'; that unavailable parts are omitted and named in 'missing'; that the workspace AI budget is consumed and the call may take up to a minute; and it spells out retry semantics with idempotency_key. That retry de-duplication does not contradict idempotentHint=false, since each new action needs a fresh key.

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?

The purpose is front-loaded and every block is substantive, but the body is one dense paragraph that blends what the tool does with a long downstream review checklist and launch choreography. The update_goal instruction is stated twice ('write the answers in with postfjord_update_goal' and 'Then change it with postfjord_update_goal'), and the show-the-person enumeration could be tightened.

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 complex generative tool with 8 parameters, nested objects and no output schema, the description supplies what the agent most needs: what gets persisted versus what does not, what the plan contains item by item, what 'missing' means, and the exact next-step tool sequence. Nothing required to invoke it correctly or to handle its result is absent.

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 88%, so the schema already documents every parameter including the nested offer object and the locale/content-language split. The description adds only indirect mapping ('posts on the goal's dates and channels') without new syntax or constraint detail, 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 — 'Starts a Flow: one goal that becomes posts, a comment-to-DM automation, a page and welcome emails' — and enumerates exactly what artifacts the plan spans. It is clearly distinguished from single-post siblings and from postfjord_draft_campaign style tools by the 'outcome over days or weeks rather than one post' criterion.

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 trigger phrases ('when the person says "start a flow" or names an outcome over days or weeks rather than one post') with three concrete example utterances, plus named alternatives for the follow-up path (postfjord_update_goal, postfjord_launch_goal). It also states the required review-and-confirm workflow and the 'wait for a clear yes' gate, so when-to-use and when-not are both covered.

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