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

Annotations already declare a mutating, destructive, open-world write; the description goes further by disclosing side effects (a book not on a shelf moves to Reading), the append-vs-replace note rule, the unit_differs rejection path, and privacy of notes. There is mild tension with idempotentHint=true, since appending a note on a day that already has one makes identical repeat calls non-identical in effect, but the description otherwise reinforces rather than contradicts the annotation set.

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?

Front-loaded with the core action and limit, and nearly every sentence adds a rule that changes how the tool is called. The phrasing is telegraphic in places ("a listener's '4 hours in' is totalMinutes minus 240, so it needs the runtime"), which costs parseability without being filler.

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 nested-entry write with no output schema, this covers auth, entry limit, dedup rule, unit consistency, note privacy, and shelf side effects. The only gap is a brief indication of what a successful call returns (e.g., confirmation of logged entries vs unit_differs), which the agent must currently infer.

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 reported top-level schema coverage is 0% for the single `entries` array, so the description must carry the field semantics — and it does: page vs minutesLeft vs note, why totalMinutes is required for audio ("4 hours in" = totalMinutes − 240), where a Kindle percent belongs, and what switchUnit and replaceNote actually do. It stops short of explaining totalPages or the interaction between trackBy and the other fields, which the nested schema handles.

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?

Opens with a concrete verb+resource: "Log a day of reading in the linked reader's journal," and immediately bounds it (one entry per book per day, up to 10 books). It also names the boundary case that belongs to a sibling — "Finishing is add_to_library" — so an agent can separate journaling from library state changes.

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?

States prerequisites ("Needs a linked Siftivo account"), the alternative tool for completion, and the escalation conditions (switchUnit when unit_differs comes back, replaceNote when the reader wants replacement rather than append). It also tells the agent when a call logs nothing at all, which is exactly the routing information needed.

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