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

Useful side-effect disclosure: 'Reading does not mark anything as read' tells the agent the read state is untouched, and the default scope (unread applied changes only) is stated. That said, this sits awkwardly against annotations of readOnlyHint=false and destructiveHint=true, so an agent cannot tell whether the call has any mutating effect at all; that tension is never resolved in the description.

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 with no filler, and the default-scope behavior is front-loaded before the override instruction. The phrasing of the first sentence is slightly convoluted ('separately from the current document by default'), but nothing is wasted.

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?

An output schema exists, so return values need not be described, and the core filter behavior is covered. For a tool with a nested arguments object, mandatory session/proof fields, and pagination, the description is thin on how the call is constructed and what the unread-vs-full history distinction means in practice.

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 50%, so the description is expected to compensate, and it largely does not. It only restates unread_only semantics already documented in the schema and says nothing about document_id, limit/offset pagination, source_path filtering, request_key idempotency, or the read_skills/expected_catalog_version envelope for a 6-parameter tool with 5 required fields.

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 first sentence names a specific verb and resource (read applied document changes) and scopes it against the current document, which separates it from the sibling native.read_document. It also implicitly distinguishes itself from native.mark_document_changes_read by stating that reading has no read-marking effect. It stops short of naming those siblings explicitly, so the differentiation is inferable rather than stated.

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?

It states the default behavior and the one condition for changing it (set unread_only to false to include read and undone history), which is a usable when-to-use rule. However, it never says when to call this instead of native.read_document or when to follow up with native.mark_document_changes_read, and no prerequisites or workflow ordering are given.

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