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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, but the description adds genuinely new behavior: it needs an access token with both read and change permissions, and the undo is strictly single-step against the last change regardless of whether the website, a token, or an assistant made it. That permission requirement and the one-step boundary are not derivable from 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 short sentences, each carrying distinct load (what it does, the one-step limit, the auth requirement), with the core purpose front-loaded. Nothing is redundant or 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?

For a no-param mutation with no output schema and full annotation coverage, the description supplies scope, the single-step constraint, and the permission requirement. The only minor gap is what a successful call returns or how the agent confirms the undo took effect.

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?

The tool takes zero parameters, so the baseline of 4 applies; there is no parameter semantics for the description to add or omit.

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 (puts back/undo) and resource (the shelf), and scopes it to the last change only. An agent can distinguish it from add_to_shelf, remove_from_shelf, and get_shelf 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?

Explicitly states the operating window: 'One step back only: a second call finds nothing to undo until the shelf changes again,' which tells the agent when the call is valid and when it will no-op. It does not name a sibling alternative (e.g., get_shelf to inspect state first), so it stops just short of full when/when-not routing.

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