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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds context those hints cannot convey: the damage is scoped to public visibility, the record survives as a draft, and it is therefore recoverable. It also adds a human-confirmation requirement, which is genuine operating guidance beyond structured data.

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?

Three short sentences, effect first, caveat last, with no filler. Every sentence carries distinct information: action, consequences, social prerequisite.

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 single-parameter mutation with no output schema and fully described annotations, nothing needed for a correct call is missing. Reversibility, blast radius, and the confirmation step are all present, and return values need no explanation here.

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?

There is exactly one parameter and schema coverage is 100%; the schema already says it is a uuid sourced from list_articles. The description adds no syntax, format, or source detail beyond that, so the baseline 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?

Concrete verb and resource ('Take an article off the customer's site') with the exact user-visible consequence spelled out: the link breaks, the form stops suggesting it. The clause 'the words stay with the team as a draft' implicitly separates it from remove_article and publish_article, so an agent can pick correctly without opening a schema.

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?

'Ask the person first' gives confirmation guidance, which is useful, but the description never states when to choose this over remove_article (full deletion) or how to undo it via publish_article. Usage is implied by the effect described rather than stated as an explicit rule.

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