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

Annotations only declare non-readOnly/non-destructive/non-idempotent; the description adds real behavior the agent can't infer — that the call may resolve an existing library title or create one, and that it sets happened/date/rating in a single call. It also prescribes a confirmation step after saving. It does not warn about duplicate risk given idempotentHint=false, which leaves one meaningful gap.

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 action and its scope, then examples, then the exclusion, then the follow-up. The example list is long but each example disambiguates a different 'happened' value, so they earn their place; the single run-on sentence carrying the workflow is the main readability cost.

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 10-parameter, non-idempotent mutation with no output schema, the description covers what the tool does, the resolution-or-create workflow, scope boundaries, and post-call behavior — enough to invoke it correctly. Missing only edge-case guidance such as re-logging the same title twice.

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 baseline 3; the description adds semantic meaning beyond the schema by describing the resolution order (title or item_id against their library, then set what happened/date/rating) and by tying the example phrasings to which fields they populate ('loved it' → no numeric rating).

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 (save) and a specific resource (the person's own reading/watching/listening/playing activity), and backs it with five concrete utterance examples that make the scope unmistakable. The phrase 'the person's own activity, not titles you are only discussing or recommending' cleanly separates it from add_item/log_event siblings.

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?

Explicitly gives a when-not-to-use rule ('not for titles you are only discussing or recommending') and frames the trigger as 'something the person just told you'. It stops short of naming the nearest alternatives (log_event, add_item, bulk_log_events), which is the only gap.

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