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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's job is to add context – it does so with the irreversibility warning, the specific NOT_FOUND error code, and the success return shape. It doesn't cover authorization requirements or whether deletion cascades to related entities, leaving a small gap.

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 critical warning is front-loaded, but the 'prefer update_offer with status archived' guidance is stated three separate times (WARNING paragraph, standalone repeat, and final sentence), which is redundant and dilutes rather than reinforces.

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?

There is no output schema, but the description supplies the exact success payload and the error code, and the confirm-flag safety mechanism is documented. Enough for an agent to call correctly and handle responses.

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 description coverage is 100% and the schema already documents both parameters (id is a UUID from search_offers, confirm must be exactly true). The description adds only 'by UUID' which the schema already conveys, so baseline 3 applies.

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 with scope ('Permanently delete an offer by UUID'), and the alternative (update_offer with status archived) makes it clearly distinct from the sibling update_offer.

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 warns the action is irreversible and names the alternative (update_offer with status: archived) plus the condition under which to prefer it (hide without deleting). No inference required.

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