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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the crucial behavior they don't convey: the default call is a dry run that changes nothing and reports what would be deleted, with real deletion only under confirm: true. It also enumerates the cascading loss (entries, sessions, pictures), which is exactly the risk context an agent needs before a destructive call.

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, front-loaded with the destructive scope, then the gating condition, then the two-step confirmation procedure. Nothing is redundant or padding.

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?

With no output schema, the description usefully covers the return behavior of the unconfirmed call ('says what would go'), and annotations carry the safety profile. It leaves unstated what happens on a nonexistent shelf or whether deletion is recoverable, minor gaps for a simple delete tool.

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 the baseline is 3, but the description adds meaning beyond the schema by framing confirm as the second step of a two-call protocol rather than a static flag. It does not explain the shelf-name vs shelf_id alternation, leaving that to the schema.

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 ('Delete one of their shelves') plus the cascade scope ('with every entry, session and picture on it'), which separates it from remove_from_shelf and delete_item. The clause 'Only when they ask to delete the shelf itself' further disambiguates from item-level removal.

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?

Gives an explicit positive condition ('only when they ask to delete the shelf itself') and an explicit procedural gate: call without confirm first, then call again with confirm: true after consent. An agent knows both when to invoke and when not to.

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