Create engine drafts (pending approval)

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

The description discloses critical behavioral traits (always pending_approval, never auto-publish, idempotent on external_ref, platform aliases, segment behavior, link appending, schedule_hint semantics, CAPABILITY). However, annotations set idempotentHint=false while the description claims idempotency on external_ref, a direct contradiction. Per rubric, this scores 1.

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?

Though long, every sentence earns its place by addressing a functional aspect—idempotency, approval flow, aliases, segmentation, style rules, and sibling relationship. Critical instructions are front-loaded, and there is no filler or repetition.

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?

Given the complexity of batch draft creation, the description covers all operational nuances: idempotency, approval chain, provider aliases, segment rules, writing style, and relationship to siblings. No output schema exists, but for a creation tool, return values are less critical and the description provides complete context for correct invocation.

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?

The description adds substantial meaning beyond schema descriptions: platform aliases (x/x_post/x_thread → twitter), segment count semantics (1 = single post, 2+ on twitter = thread), link appended at approval, schedule_hint 'optimal' or future ISO datetime, and brand tag distinction from BrandVoice. This far exceeds the 67% schema coverage.

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?

The description opens with a specific verb ('Submit') and resource ('batch of platform drafts for one engine artifact'), clearly stating what the tool does. It also distinguishes from sibling create_digest_drafts by explaining they share the same mechanism but this name is preferred, providing clear differentiation.

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 directs the agent to call prompt_suggest first and base the prompt on the top result, and to read recent posts via list_posts to match voice. It also advises to prefer this name over create_digest_drafts for new integrations and notes it is safe for draft-only tokens, giving clear when-to-use and exclusions.

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