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

While annotations already set destructiveHint=true, the description goes further by disclosing the specific refusal behavior for published articles and the permanent nature of the deletion. It clarifies that the tool only operates on never-published drafts, which is not captured by the annotations alone. This adds meaningful behavioral context beyond the structured flags.

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 three sentences, each earning its place: the first states the core action and condition, the second provides the key alternative and its behavior, and the third narrows usage to test/abandoned drafts. It is front-loaded with the most critical information and contains no fluff.

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 tool with two well-documented parameters and clear sibling relationships, this description is complete. It covers when to use it, when not to, what the alternative is, and the irreversibility. No output schema exists, so no return-value expectations are needed. An agent has all information required to invoke this correctly.

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%; both 'slug' and 'shelf' have descriptions in the schema. The tool description itself does not elaborate on parameters, but that is unnecessary given the schema already documents them. Following the baseline for high schema coverage, a score of 3 is appropriate—no additional value is provided, but none is needed.

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 states exactly what the tool does: 'Permanently delete a Creative Library draft' with a specific condition ('NEVER been published'). It clearly distinguishes itself from the sibling creative_unpublish_article by explicitly calling it out. The verb-resource pair is unambiguous and the scope is precise.

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 explicit guidance: it says the tool is 'Refused for any article with publication history' and directs the agent to 'use creative_unpublish_article to take a live page down instead, which keeps the draft.' It also states when it should be used: 'only to clear test or abandoned drafts.' This leaves no ambiguity about selection.

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