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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, but the description adds what annotations cannot: nobody else is told, no email goes out, and the reminder surfaces via whats_new and in every tool result. It also discloses a non-obvious side effect — reminding about a tracked item 'puts the item out of sight until then' — plus the time-zone reading rule. Only the absence of any output-shape or failure-mode detail keeps it off a 5.

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 purpose sentence before branching into privacy, identifier sources, and time semantics. Dense but nearly every clause carries information an agent needs. The parenthetical about out-of-sight items is slightly buried mid-sentence, but nothing is padding.

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 two-parameter write tool with no output schema, the description says where the result becomes visible (whats_new, tool results) and how to undo it (resolve_item), closing the gaps annotations leave open. An agent has everything needed to call it correctly on the first try.

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 is 3, and the description goes beyond it by enumerating the exact source tools that produce the `about` identifier (check_inbox, get_thread, whats_new, track_item) rather than just 'package_id or item_id'. It also adds an inference rule absent from the schema: the server does not parse 'Friday', so the agent must resolve which day the user means before formatting `at`.

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 action (surface an item back to attention) with a specific trigger (a user-chosen time) and names both object types it accepts: a package or a tracked item. This separates it cleanly from track_item, resolve_item, and whats_new, which appear in the same description as distinct lifecycle stages.

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?

Explicit routing: pass package_id from check_inbox, get_thread, or whats_new, or the item_id of something track_item is watching. It also states the re-invocation semantics (calling again with a new time moves the reminder) and the teardown path (resolve_item clears it). When-to-use and how-it-relates-to-siblings is fully covered.

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