Schedule / draft a post

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

Beyond annotations (readOnlyHint=false, openWorldHint=true), the description exposes critical behaviors: it discloses that scheduling 'will push it to a live audience', that TikTok values must never be invented or carried over, that an incomplete TikTok block is 'rejected naming the fields still missing', and that in mixed requests only TikTok is refused. It also mentions the 403 on authorization mismatch, adding substantial operational context.

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 description is dense and front-loaded, with the core purpose in the first sentence. However, it is quite long and somewhat repetitive (e.g., emphasizing 'from the human' in multiple forms). Each sentence adds value, but a minor trim would improve readability without losing information.

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?

Platform-specific requirements, style guidelines, and failure modes are thoroughly covered. However, the description does not explain what a successful call returns (no output schema is provided), nor does it mention how mediaUrls relate to the sibling upload tools (prepare_media_upload, upload_media, finalize_media_upload) — leaving some integration ambiguity for an agent.

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 100%, but the description adds a wealth of meaning: TikTok fields must be human-provided and sourced from get_tiktok_creator_info; Pinterest requires exactly one image URL and maps content to the pin description (≤500 chars) and title (≤100 chars); `brand` is clarified as NOT an AI BrandVoice profile. This significantly enriches what the schema alone provides.

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 'Create a post. Provide a future ISO scheduledAt to schedule it (omit for a draft).' which clearly states the verb, resource, and the two modes (schedule vs draft). It also distinguishes from siblings by explicitly naming the capability (`draft` vs `publish`) and platform-specific behavior.

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?

It gives direct prerequisites: 'Call get_tiktok_creator_info first...', 'call list_boards first to get a valid boardId', and 'Before drafting, read the account's recent posts with list_posts'. It also warns against using scheduledAt with a draft-scoped token ('gets a 403') and explains when to omit scheduledAt, providing clear when-to-use and when-not-to-use guidance.

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