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

Annotations already flag destructiveHint and idempotentHint, but the description goes further: it discloses effects (public link stops working, tools lose access, plan slot freed), the confirmation gate, and the authorization constraint. This is exactly the consequence-level detail an agent needs before an irreversible 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?

Front-loaded with the action, and every clause carries real information. The long compound sentence about the catalog's disappearance is slightly awkward ("these tools cannot reach it afterwards") but earns its place through consequence detail.

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 two-param tool, everything an agent needs is present: effect list, confirmation workflow, and ownership restriction. An output schema exists, so the absence of return-value documentation is not a gap.

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 schema already documents both params. The description nonetheless adds workflow meaning to confirm — it is the second leg of a dry-run approval cycle, with the pre-confirm output surfaced as requiresConfirmation — which the schema description alone only hints at.

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?

Opens with a specific verb and resource ("Delete one of the merchant's catalogs"), which cleanly separates it from siblings like delete_products and edit_catalog. An agent knows immediately this permanently removes a catalog object.

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 two-phase protocol: it only runs with confirm: true, and without it nothing is deleted and the response lists candidates under requiresConfirmation. It also names the exclusion — shared catalogs are refused, only the owner can delete — so the agent knows when not to call it.

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