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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly covered. The description still adds real context: the cascading scope (update layers and links are destroyed), irreversibility ("Cannot be undone"), and the confirm guard, which the annotations do not express.

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 tight sentences with the destructive action and cascading scope front-loaded, followed by the precondition and the reversible alternative. No sentence is redundant.

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 delete tool with no output schema, the description covers what is deleted, the confirm requirement, irreversibility, and the safer alternative. Combined with annotations, an agent has everything needed to call it correctly and cautiously.

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 id, brain, and confirm are already documented in the schema, including that confirm is the exact title. The description only reinforces the confirm requirement rather than adding new syntax or format detail, so the baseline 3 is appropriate.

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 (deletes), resource (one memory), and unusual scope (its update layers and links), so an agent knows exactly what is removed. It is clearly distinguishable from the sibling memory_archive, which it explicitly calls out as the reversible counterpart.

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?

Names the alternative (archiving) and the condition that selects it (reversibility), and states the precondition for using this tool (confirm must equal the memory's exact title). When-to-use, when-not-to-use, and prerequisites are all present.

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