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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), so the description only needs to add context. It does disclose one real side effect ("creating the list if new") and where to source external_id (lookup_item), but says nothing about duplicate handling, whether repeat calls stack duplicates (non-idempotent), or what happens on partial failures across eleven modes.

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?

Dense but zero fluff: a single front-loaded enumeration where every clause carries a distinct kind. It is hard to scan as one run-on sentence and could be broken into a list, but no sentence 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?

For an eleven-mode, 40-parameter mutation tool with no output schema, the description covers the shape of each mode but not the full parameter-to-mode mapping and omits conflict/duplicate behavior. The pointer to the `describe` tool partially compensates, leaving it adequate but incomplete.

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?

With 40 parameters and 50% schema coverage, baseline is 3. The description groups parameters by kind and adds genuinely new meaning for `external_id` (pass the id from lookup_item for an exact match) and the challenge_pick choice of prompt vs slot_id, but much of the parenthetical text merely restates what the schema descriptions already say ("For shelf_entry: YYYY-MM-DD"), and many parameters such as line, note, year, platform, event_date remain unexplained anywhere.

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 states a clear verb (add) and enumerates the eleven concrete kinds of things that can be added, each with a short gloss ("list (a new list)", "event (a finish or rewatch with a date)"). An agent can tell what the tool creates, but it gets no differentiation from siblings that appear to do the same job (add_to_list, add_to_shelf, create_list, create_shelf, pin_to_page, add_item).

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?

Per-kind glosses imply when each `what` value applies, and the final sentence points to `describe topic collections` for the argument list. However, there is no statement about when to prefer this tool over the overlapping dedicated siblings, and no exclusions or prerequisites for mutations like creating a list or pinning.

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