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

Annotations declare readOnlyHint=false (mutation expected) and destructiveHint=false (non-destructive), so the description's 'Create' is consistent with annotations. The description adds important behavioral detail about TikTok's two publishing modes, including that UPLOAD creates an inbox draft to be finished in the TikTok app, and that X/Threads threads are posted as chained replies. However, it does not disclose scheduling semantics (e.g., date format, timezone), limits, or error behavior beyond what the schema already shows.

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 a compact multi-sentence paragraph that front-loads the core purpose first, then adds targeted platform-specific detail. Every sentence earns its place: the first states the primary function, and the following sentences address non-obvious platform behaviors. It is appropriately sized for a complex multi-network scheduling tool.

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?

The tool has a very large schema with 10 required top-level parameters and many nested options, but no output schema. The description correctly focuses on the cross-cutting behaviors that are non-obvious from the schema, such as TikTok's two publishing modes and thread building. However, it lacks guidance on how to structure the scheduledFor variants (DRAFT/NOW/SCHEDULE with date), which is required and not obvious from a large schema. It also doesn't clarify whether an empty targets array is meaningful or how to use the array-of-targets structure with sibling tools.

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 carries the burden of explaining parameters. It does add value: it explains the scheduledFor concept ('scheduled item'), the meaning of TikTok postMode values (DIRECT_POST vs UPLOAD), and the segments array behavior for X/Threads thread publishing. It doesn't enumerate all target array parameters or confirm the required nature of all target arrays, but it explains the most complex cross-network semantics. Given 10 required params with zero schema descriptions, the description meaningfully aids parameter invocation.

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 clearly states the tool's purpose: create a scheduled item that publishes to one or more connected social accounts. It uses a specific verb ('create') and resource ('scheduled item'), and its multi-network publishing scope distinguishes it from siblings like list_posts or delete_post. It also covers TikTok post mode nuances that clarify what the tool does for specific targets.

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?

The description provides a clear context for when to use the tool (creating scheduled posts across social accounts) and includes usage guidance for TikTok's DIRECT_POST vs UPLOAD modes. It does not explicitly name alternative tools or say when not to use this tool versus siblings like update_post or reschedule_post, but the context is clear enough for an agent to select it correctly.

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