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

With no annotations provided, the description carries the full behavioral burden and does so: it discloses irreversibility ('content is not recoverable'), the residual artifact ('only an audit row (no content) is kept'), the destructive blast radius of the default scope, and the single-use nature of the nonce. These are exactly the consequences an agent must weigh before invoking a destructive tool.

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?

The irreversibility warning is front-loaded in the first clause, scope semantics follow, the prerequisite is stated before the argument list, and the Args block is terse with no filler. Every sentence carries operational weight.

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, so return-value detail is unnecessary, and the description fills the remaining gaps for a high-risk mutation: signing flow, prerequisite call, scope defaults, side effects, and audit behavior. Nothing an agent needs to call this correctly 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 0%, so the description must compensate, and it documents all seven parameters, including provenance (timestamp and nonce come from memory_prepare), the single-use constraint on the nonce, the enum-like scope values with default, and a concrete limit on reason (max 200 chars). This adds meaning the bare schema cannot supply.

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?

The description opens with a specific verb and resource ('PERMANENTLY delete a memory') and immediately qualifies the operation type (hard delete / right-to-be-forgotten). It also distinguishes the two destruction modes ('chain' removes EVERY version vs 'version' removes only this row), which an agent needs to separate this from siblings like memory_deletions or memory_update.

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?

It states a clear precondition ('Call memory_prepare with operation "delete" and the same arguments first') and explains which scope value to pick for which intent. It does not, however, name the adjacent alternatives an agent might reach for (e.g., memory_update to amend instead of destroy, or memory_deletions to inspect past deletions), so routing guidance stops short of explicit when-not-to-use.

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