Publish Draft

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

The description details the exact state transitions (to PENDING or SCHEDULED), the queuing behavior per platform, and the irreversible nature of publishing ('cannot be recalled'). It also lists failure conditions (disconnected account, missing privacyLevel) and the remedy (update_post), which is far beyond what the annotations convey.

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?

Every sentence carries essential information—purpose, conditions, behavior, failure modes, and alternatives—without redundancy. The structure is logical: state the allowed statuses, explain the two modes, then list pitfalls and next steps. No filler or irrelevant detail.

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 description covers the full workflow: prerequisites (post must be DRAFT or SCHEDULED), how the tool behaves in each scenario, what can go wrong (disconnected accounts, missing privacyLevel), how to fix it (update_post), and what to do next (check list_post_results). It also clarifies the boundary with create_post, making it fully self-contained.

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 practical meaning to each parameter: scheduledAt's omission or past value triggers immediate publishing, timezone is explicitly noted to not shift the instant, and id is contextualized as targeting a DRAFT or SCHEDULED post. This enriches the schema's bare descriptions.

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 verb 'publish' and the target (a post), and explicitly distinguishes the two modes: publishing immediately or scheduling. It also specifies the allowed statuses (DRAFT and SCHEDULED) and the error for others, leaving no ambiguity about what the tool does.

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 explicit when-to-use guidance by listing acceptable statuses and explicitly stating 'Not for new content, use create_post'. It also tells users to check list_post_results afterwards, which is actionable follow-up guidance.

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