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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds behavior an agent cannot infer from them: the safe-by-default dry run, the count-only preview response, and the exact confirmation string gate. This is exactly the extra context a destructive tool needs.

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 sentences, zero waste, and correctly front-loaded: what it deletes, then the safety default, then the hard precondition. Every clause carries load.

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 bulk-delete with an output schema already covering the return shape, the description supplies everything an agent needs: scope, default behavior, the confirmation gate, and the explicit user-consent requirement. Nothing material is missing.

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%, so both parameters are already fully documented in the schema. The description restates the confirm string value and dry_run default rather than adding new meaning, which lands at the baseline for high-coverage schemas.

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) and resource (all memories) with an explicit scope qualifier: 'all memories this connection can reach.' That scope wording cleanly separates it from the singular siblings delete_memory and delete_entity.

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 explicit usage conditions and a hard exclusion: the default is a dry run reporting only a count, and the real deletion requires dry_run=false plus an exact confirm string. It also states 'Never call this without the user explicitly asking to erase everything,' which is the strongest possible when-not guidance for a destructive tool.

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