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

Goes well beyond the annotations: it discloses exactly what data leaves the workspace (no accounts, posts, sequences, team members or HTTP keys), that the flow becomes publicly visible, that Ignix review happens first, and that resubmission while pending mutates instead of duplicating. This substantiates the destructiveHint=true and idempotentHint=true flags with concrete consequences instead of leaving them abstract.

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?

Four tight sentences, each carrying distinct information: what it does, that review intervenes, what the snapshot excludes, the consent gate, and resubmission behavior. What gets published is front-loaded before the caveats.

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?

Complete for a no-output-schema mutation: an agent knows the preconditions, the exposure, and the repeat-call semantics. The only gap is the post-call state (e.g., that the flow enters a pending-review status the agent can check) – implied by 'waits for review' but not stated as an outcome.

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?

At 75% schema coverage the schema already documents description, idempotencyKey, and affiliateUsername, and the description adds no syntax or format detail for any of them. It only reinforces intent ('credited to their brand', 'their texts and links public'). Baseline 3 is warranted – the schema carries the parameter load.

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?

Specific verb+resource+destination: sends one of the user's own flows for review so it appears in Templates and on a public gallery page. The scope ('one of the user's own flows', credited to their brand) and the review gate make it unmistakably distinct from share_automation, import_shared_automation, and create_automation without needing the sibling schemas.

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 a hard precondition ('Only when the user asked for it or agreed') and a behavioral rule for repeat calls ('Sending it again while it waits for review updates it'), which covers the main ambiguity an agent would hit. It never names a sibling alternative, so the agent must infer that sharing vs. importing vs. gallery-submitting are different tools.

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