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

Annotations declare destructiveHint=true and openWorldHint=true, but the description goes well beyond them: it discloses the human-approval requirement, the account-connection prerequisite, plan-based limits on live pages and monthly updates, and the asynchronous multi-second check. It enumerates the three possible outcome values and the follow-up action for each, which is the kind of behavioral detail annotations cannot carry.

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 gating condition and the confirmation requirement lead, and the outcome-handling list is compact and scannable. It loses a point for loose phrasing such as 'publish the user's changes together' and the slightly tangled plan-cap sentence, which could be tightened.

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 destructive, open-world mutation tool, the description covers prerequisites, user consent, plan constraints, async timing, and every return-state branch. Even though an output schema exists, the outcome interpretation is essential for correct follow-up behavior and is fully supplied.

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%, so page_id and base_updated_at are already documented, including the conflict-detection purpose of base_updated_at. The description adds nothing about either parameter's format or how a conflict surfaces, so the baseline of 3 applies.

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?

States a specific verb and resource ('Publish the draft on the user's site') plus the gating condition (automatic checks must accept it). This clearly separates it from publish_instagram_post, preview_page, and update_page, which an agent could otherwise confuse with it.

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 says to ask the user before publishing, names the required connected Instagram account, warns about plan caps (Free = home page only), and routes to get_page with review_state when the outcome is 'checking'. It also tells the agent what to do on rejection: tell the user, fix the page, publish again.

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