Edit notes, shapes, tables…

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

Annotations only establish readOnly=false, destructive=false and idempotent=true; the description goes well beyond them by describing partial-update semantics (only passed fields change, non-applicable fields are ignored), the validation error on an invalid color, immediate persistence as a new board revision, live propagation to open browsers, undo via Ctrl+Z, and the return value. This is exactly the write-path behavior an agent needs and 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?

Front-loaded with purpose, then behavior, then the sibling pointer. The long parenthetical item list and the many clauses are dense but each sentence carries distinct information; only the enumeration of item types is arguably padded, costing it a perfect score.

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 bulk-mutation tool with no output schema, the description covers the full picture: what can be changed, partial-update behavior, error behavior, persistence and undo, live effects, and what is returned (count of changed items). Nothing needed to call it correctly is missing.

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 per-field documentation is already handled and the baseline is 3. The description exceeds that by adding cross-field semantics not present in the schema: only the fields you pass are changed, fields not applicable to an item type are silently ignored, multiple items can be updated per call, and the color error lists valid alternatives.

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 (change/edit) and resource (existing items), enumerating the item types covered: notes, text, shapes, sections, tables, charts, connectors. It also explicitly routes mind map nodes to the sibling update_nodes, so an agent can distinguish it from update_nodes, add_items and delete_items without opening any schema.

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?

It gives clear context for when this applies (modifying existing items, including bulk multi-item edits) and names the alternative for mind map nodes. It stops short of full when-not guidance — it never contrasts itself with add_items for creation or delete_items for removal — but the routing rule to update_nodes is explicit.

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