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

Annotations already establish this as a safe, idempotent, non-destructive read, so the description earns credit for what it adds: the change-tracking semantics (what changed since the account last looked, with date/source/provenance) and the collapsed hierarchy behavior of the everything view. It stops short of saying whether reading changes marks them seen (a separate mark_changes_seen sibling exists) and gives no rate/limit or result-size caveats beyond the schema.

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?

Everything is packed into one long semicolon-chained sentence; the scope is front-loaded, but the density makes it harder to scan than a broken-out list of what is returned. Most clauses carry real information, though a few (page and source per item) sit close to what the schema and annotations already imply.

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 and a fairly complex return shape, the description does the necessary work by enumerating the returned sections, including change records and their provenance. The remaining gap is operational: it never states pagination behavior at the top level or whether the 'since last looked' window is affected by other tools.

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%, so the enum meanings of view/kind, cursor semantics, filter, and the folder_id omission rule are already documented in the schema. The description adds only marginal framing beyond that, echoing the everything-view aggregation and the folder_id-omitted top-level case rather than introducing new syntax or constraints.

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 enumerates precisely what is returned: one folder (or the account top), its subfolders, the entities inside by kind with page and source, saved-search matches, and recent changes. That is a clear resource+content statement an agent can match to a browsing need. It never names a sibling (list_folders, get_search_matches, search) as the thing it is not, so differentiation is left implicit.

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 when-to-use or when-not-to-use guidance. It notes the existence of the everything view but not when an agent should pick it over contents, and it does not say when to call get_folder versus list_folders, search, or get_search_matches, even though it duplicates saved-search match retrieval that a sibling also offers.

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