Create thread

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

Annotations state readOnlyHint=false and openWorldHint=true, but the description adds substantial behavioral detail: the exact composite posting sequence, partial-failure behavior ('STOP and return what already went up'), per-post cost estimates, the confirm requirement, link-warning duty, and the absence of native scheduling. This goes far beyond what annotations alone convey and contains no contradiction.

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?

Each sentence earns its place: composite mechanics, content fidelity, confirm requirement, failure handling, cost, link warning, and scheduling limitation. The most important purpose statement is front-loaded, and the description remains compact given the number of critical constraints it covers.

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 composite mutation tool with no output schema, the description covers the full invocation contract: how to structure the thread, what content to use, the confirmation gate, failure semantics, cost implications, link warning, and scheduling impossibility. The only minor gap is reply_settings, but its enum values are self-explanatory and the schema carries that information.

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 only 33% (only `confirm` is described). The description compensates meaningfully for `posts` by specifying that it must be the user-supplied array and that no posts may be invented, and for `confirm` by clarifying it is required once for the whole thread. However, `reply_settings` is left completely unexplained in both schema and description, and media handling is only implied.

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 composite behavior: 'publish the first post, then chain the rest as replies (in_reply_to of the previous).' This clearly identifies the resource (a thread of posts on X) and the verb (create/publish), and the composite nature distinguishes it from single-post siblings like create_post or reply.

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 gives clear operational guidance: use only user-supplied copy, require confirm=true once, stop on later-post failure, warn before posting links, and never simulate scheduling because X has no native schedule. It does not explicitly name the sibling single-post tools as alternatives, but the composite distinction and the scheduling exclusion provide strong contextual usage direction.

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