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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description does add real value beyond them: result ordering, the fields returned per change, the documented blind spot about which AI app acted, and the pagination mechanism. It stops short of stating default page size or default date window, which matter for a list tool with all-optional parameters.

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 compact sentences, front-loaded with purpose, then a caveat, then the pagination note. No filler or marketing language. The cursor sentence largely duplicates the schema description, which is the one trim available.

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?

With no output schema, the description correctly compensates by naming the returned fields and the sort order, and it explains how to page. The stated limitation on AI-app attribution preempts a likely agent assumption. Remaining gaps are minor: defaults for `perPage` and the date range, and how to interpret a null cursor at the end of results.

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 description coverage is 100%, including the enum meanings for `via` and `resourceType`, so the schema already carries the semantics and the baseline of 3 applies. The one parameter the description touches, `cursor`, only restates the schema's own 'metadata.nextCursor of the previous page' wording. Nothing is added for `from`/`to`/`perPage` semantics such as defaults or inclusive/exclusive boundaries.

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 with scope ('list what AI apps changed in the workspace'), plus the ordering ('newest first') and the shape of each returned change. It even discloses a limitation ('does not tell apart which AI app made a change'). It never names the nearest sibling (list_operations), so sibling differentiation is left implicit rather than explicit.

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 is implied rather than stated: an agent can infer this is the audit view for AI-app-driven mutations, satisfying the 'when'. There is no explicit 'when not', no mention of how this relates to list_operations or list_messages, and no prerequisites (e.g., whether a date range is required in practice).

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