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

Annotations supply the safety profile (destructiveHint=true, idempotentHint=true, readOnlyHint=false), and the description adds real value on top: the non-obvious guarantee that removing a layout item does NOT delete the underlying sheet attribute, and the asymmetry that removing a title-level field drops it from the layout entirely. The remaining gap is the return shape, which is covered by the output schema.

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 core action is front-loaded in the first clause and each subsequent sentence handles a concrete confusion case rather than padding. The parenthetical-heavy phrasing and semicolon chains make it dense to parse, but nothing is redundant.

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 destructive mutation with an output schema and modest branching (two identification modes), the description covers consequences, alternatives, and side effects thoroughly. The only meaningful omission is the peekId parameter, which is central to scoping the operation but left entirely undocumented.

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 0% with three params and none required, so the description must carry the load. It does well on two: layoutItemId is sourced ('returned by peek.read') and attributeCode's first-match behavior is spelled out, which also implies the either/or selection logic. However, peekId is never mentioned at all despite being a distinct parameter whose meaning is unexplained and whose requiredness is ambiguous.

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 ('Remove an item from a record layout') and immediately scopes it against two lookalike operations (form fields via form.update, sheet attributes via sheet.remove_attribute). An agent can distinguish this from peek.add_layout_item, peek.reorder_layout, and sheet.remove_attribute 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?

Explicit routing is given for every adjacent case: forms use form.update `removeFields`, underlying attributes use sheet.remove_attribute, and fields under the title that should be moved rather than removed use peek.reorder_layout `underTitle`. It also names the 'remove cover/icon' scenario as the intended use of attributeCode.

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