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

Annotations already flag destructiveHint=true, but the description adds critical context: permanence, no recycle bin, scope limited to the signed-in user's own notifications, and the human-confirmation gate. This goes well beyond the structured 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, dense sentences with the critical permanence warning front-loaded, followed by the single vs batch distinction and the human-confirmation rule. No filler or redundancy.

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?

The description plus the fully covered schema give the agent the scope, destructive nature, single/batch behavior, and human-authorization requirement needed to invoke the tool correctly. Error or return behavior is not described, but no output schema exists and it is not critical for a delete operation.

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 baseline 3 applies. The description confirms the single/batch split and the human-supplied confirmation rule, but this largely mirrors the schema's parameter descriptions rather than adding new semantic detail.

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 ('delete'), resource ('notifications'), scope ('signed-in user's own'), and permanence. This clearly distinguishes it from notifications_get, notifications_mark_read, notifications_send, and other delete tools in the sibling list.

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?

Provides explicit operational guidance: single deletion by id vs batch requiring human-set confirm/confirmation_phrase, and an explicit never-fill-in restriction. It does not name sibling alternatives like notifications_mark_read, but the context for when to use this tool is clear.

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