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

The annotations already declare non-read-only, non-destructive, non-idempotent, and closed-world behavior. The description mostly restates the non-destructive aspect with 'nothing is deleted' and says fields belong in params, but it does not explain what each action changes, required permissions, side effects, or per-action idempotency. For a 26-action mutation tool, this is minimal behavioral context beyond 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?

The description is front-loaded with the key constraint ('nothing is deleted') and then organized by resource category. The action list is dense but purposeful because the tool multiplexes many actions. It wastes little space, though repeating all enum values makes it long and the opening 'Organize' is not precise.

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 complex multi-action tool, the description covers all action names and groups them, and it correctly directs the agent to guide for action-specific fields. However, it provides no per-action semantics, required-parameter hints, or outcome details beyond non-deletion. Given the sibling guide tool exists, this is adequate but not fully self-contained.

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 already 100%, so the baseline is 3. The description adds limited meaning: 'Fields go in params' and brief field hints for update_design (title, position, size) and add_items (notes, shapes). It does not explain required fields for the other actions, instead pointing to guide.

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 gives a broad umbrella verb ('Organize') but immediately enumerates concrete action categories: pages, folders, groups, screens, canvas, and comments. This lets an agent see it is a multi-action management tool, and 'nothing is deleted' distinguishes it from the delete sibling. It is not a 5 because the opening verb is vague and it does not clearly distinguish its update actions from the edit sibling.

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?

Usage is implied through the action list: if the task matches create_page, update_group, comment, etc., use this tool. The statement 'nothing is deleted' gives one negative boundary, steering deletions toward the delete sibling. However, there is no explicit when-to-use vs edit/design guidance, and the agent must infer alternatives.

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