Delete memory

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description goes further by disclosing that this is a reversible removal: the memory disappears from search and reads while "every saved version is kept," plus the concrete restore command. This is exactly the post-destructive recovery context an agent needs to reassure a user.

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, zero waste. The precondition is front-loaded and the recovery mechanism follows as supporting context; nothing is repeated from the title or schema.

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 two-param mutation with no output schema, the description covers the critical unknowns: reversibility, visibility impact, and the restore path. The one gap is that memoryId's meaning and how to obtain it is left entirely to the schema, which does not describe it.

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 only 50%: `brain` is documented (personal brain is "personal") but `memoryId` carries no description in either the schema or the prose. The description never mentions any parameter, so it does not compensate for the undocumented id.

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?

"Delete a Brain memory" names a specific verb and resource, and the description immediately qualifies the semantics as a soft delete where the memory "leaves search and reads" but versions persist. That is distinguishable from siblings like update_memory or get_memory_versions without opening any schema.

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?

The trigger condition is explicit and restrictive: only "when the user explicitly asks to remove a saved fact." That implicitly excludes correction-style edits (which belong to update_memory), but no sibling tool is named as the alternative the way a 5 would require.

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