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

Goes well beyond the annotations: it discloses the social side effect ('Other members see who checked it off'), the exception to the 24-hour plan undo system, the reversal mechanism, and the authorization requirement. These are exactly the mutation-context facts an agent cannot infer from readOnlyHint=false / destructiveHint=false / idempotentHint=false, and the non-idempotent framing ('opposite value reverses it') is consistent with the annotations.

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?

Three tight sentences: core action and inverse first, then the visible side effect, then undo/authorization caveats. Every clause carries information an agent needs; nothing is padded.

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?

With no output schema and no parameter descriptions, the description covers the mutation's consequences, undo behavior, and permission gate, which is most of what matters. It stops short of saying what happens when the item is already in the requested state or what the response contains, but the remaining gap is small for a 3-parameter toggle.

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 description coverage is 0%, so the description must carry parameter meaning, and it does explain the one non-obvious parameter (done=false un-checks). However, list_id and item_id are left entirely to their regex patterns, with no explanation of where those IDs come from (presumably zarok_get_shared_lists), so compensation is only partial.

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 and resource ('Marks one shared list item done') and explicitly describes the inverse operation via done=false, which pins down the toggle semantics. This clearly separates it from zarok_add_shared_list_item, which creates items rather than changing their state.

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?

Gives the condition for both directions (set done, or set done=false to un-check) and states the role prerequisite ('Requires an editor or owner role'), so an agent knows when the call will succeed. It does not name any alternative tool, but no real alternative exists in the sibling list, so the gap is minor.

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