List what changed since the reader read it

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

The annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, no open world), yet the description adds substantial behavior: the paused-sharing branch returns {paused: true, message}; the normal response shape is {documents: [{path, blocks, at}], version}; and truncated lists gain omitted and narrow. It also warns that the tool reveals which documents the reader has read, a privacy trait nothing else exposes; only a few minor details (pagination depth, cost) are absent.

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?

The content is front-loaded with the core definition and the disambiguation before the response details. The sentences are dense, semicolon-heavy run-ons, but nearly every clause carries information, so there is only slight structural cost in readability.

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?

There is no output schema, and the description fully compensates by documenting the normal response shape, the version field, the paused branch, and truncation metadata. For a one-parameter read tool with rich annotations, nothing required to call it or interpret its results is missing.

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?

The schema fully documents the single path parameter (100% coverage), including relative vs absolute forms and folder trailing-slash semantics, so the baseline is 3. The description restates the acceptance-scope behavior of path (one document or a folder subtree) but adds no new syntax or edge-case detail beyond the schema.

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 uses a specific verb and resource: it lists documents the reader has read whose blocks changed since the last read, ordered newest change first. It also distinguishes itself from sibling tools by name: folio_digest covers all changes (read or not), and folio_reads with its path covers marks on one page.

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 when to use the tool ('what changed for the reader') and when not to use it, naming two alternatives and the condition that selects each: folio_digest for every folder change over a period, folio_reads for the marks on one page. The scoping effect of the path parameter ('only that document or those under that folder') is also spelled out.

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