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

Annotations only declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false; the description goes well beyond them. It discloses the full write protocol — the call returns status='confirmation_required' with an action_id and a plan_token, and nothing is persisted until confirm_action runs. It also discloses server-side numbering continuation, which is otherwise invisible behavior. With no output schema, this is exactly the context an agent needs before invoking.

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, then the ordering/numbering semantics, then the confirmation protocol in a clearly labeled block. Every sentence carries information, though the 'breaking a task into steps is usually several points at once' rationale is slightly padded justification for a design choice the agent cannot change. No wasted or repeated text.

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 mutation tool with no output schema and no annotation coverage of the write path, the description supplies the return shape (status, action_id, plan_token) and the prerequisite step. What remains thin is the two identifier parameters and what happens after confirm_action (e.g., whether items appear immediately on the assignment). Complete enough to call correctly, not fully complete.

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% across three required parameters, so the description must compensate and only partly does. It explains 'items' well (order is preserved, the server continues the task's existing numbering, pass a list), but assignment_id and project_id get no explanation at all — notably why both are required together. Partial compensation for a full coverage gap warrants a 3.

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 first sentence gives a specific verb plus resource plus scope: add one or more checklist points to an assignment. That is enough to separate it from the sibling erp_toggle_checklist_item (toggle vs. add) without naming it. It stops short of an explicit sibling contrast, so it lands at 4 rather than 5.

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?

The description tells the agent to batch points into one call ('takes a list rather than one line per call'), which is real when-to-use guidance. It also states the mandatory two-step flow: the tool is proposed only, and the write occurs after confirm_action. It does not name the alternative for marking an item done, so no explicit exclusion is offered.

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