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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds meaningful context beyond that: permanence, irreversibility, and an explicit user-confirmation requirement before invocation.

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?

Two sentences, no filler, with the destructive consequence and the confirmation requirement front-loaded where an agent will act on them.

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?

An output schema exists and annotations carry the safety profile, so the description need not explain returns. It covers the essential caution well, though it says nothing about behavior when an id does not exist or about partial failures in a multi-id batch.

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% and the parameter is fully documented in the schema with an example. The phrase 'one or more' and 'by id' lightly reinforce the batch/array semantics but add nothing the schema does not already state.

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 ('Permanently delete ... memories') and narrows scope with 'by id', which implicitly separates it from delete_all_memories. It never names the sibling explicitly, so the differentiation is inferable rather than stated.

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 one real usage condition — confirm with the user before calling — which is valuable. But it offers no guidance on choosing between this and delete_all_memories, delete_entity, or update_memory when the user's intent is ambiguous.

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