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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety bar is low. The description still adds real behavioral facts beyond them: results are ordered newest-first and paging is driven by a revision number via `after`. Return shape is left to the output schema, which exists.

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?

A single compact sentence with the resource, ordering, and change types front-loaded, followed by the paging hint. No redundant or filler wording.

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 two-parameter read tool with an output schema and full annotation coverage, the description supplies what's missing: ordering, pagination mechanics, and what counts as a change. Only the relationship to sibling tools like atlas_changes is unaddressed.

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 both parameters are documented there, setting the baseline at 3. The description reinforces that `after` is a revision number used for paging, but contributes little beyond the schema's own 'Only changes after this revision; default 0'.

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+resource: it returns 'confirmed changes between the revisions of a published dataset', and enumerates the kinds of changes (plans added, removed, moved fields). That distinguishes it from a generic changelog, though it never names the siblings atlas_changes or atlas_compare that an agent would otherwise confuse it with.

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?

Usage context is implied by 'published dataset' and 'confirmed changes' (as opposed to draft/global changes), and it tells you how to page. But there is no explicit statement of when to choose this over atlas_changes, atlas_compare, or atlas_dataset_get, so the agent must infer the split.

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