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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: when `changed` is true the body is an unpublished draft that only goes live via publish_article — a distinction an agent could not derive from structured fields alone.

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?

Two tight sentences with no filler, and the draft-state caveat is placed after the core resource statement. It is slightly cryptic — the first sentence is a sentence fragment and the reader must guess that `body` and `changed` are returned fields rather than arguments.

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-resource read with one parameter and no output schema, the description covers the essential ambiguity: that the returned body may be an unpublished draft awaiting publish_article. What remains thin is the general shape of the returned article, though the annotations and simple schema carry most of the remaining load.

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% and the sole parameter `article_id` is documented in-schema as a uuid obtainable from list_articles, so the baseline of 3 applies. The description adds no parameter-level meaning; `body` and `changed` it references are response fields, not inputs, which is never made explicit.

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 identifies a specific resource (one help article) and what it carries (`body`, small Markdown), which is enough to distinguish it from list_articles and publish_article. However, it is written as a noun phrase fragment rather than stating the verb 'retrieves', so the purpose is inferred from the name rather than asserted.

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?

There is no explicit guidance on when to call this versus list_articles (bulk) or when a draft vs published view matters. The mention of publish_article is a workflow hint about the `changed` state, not an alternative-selection rule, so an agent must infer usage conditions on its own.

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