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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description's added value is the 'Proposes only' note, which tells the agent nothing is applied immediately, but it omits what a proposal returns, how it is confirmed or discarded, and that visibility changes can expose data to other household members.

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 short sentences with the scope stated first and the propose-only caveat second. No wasted words, though 'Proposes only' is terse enough to be ambiguous without further explanation.

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 mutation tool with no output schema, the description covers the target and the fields but not the proposal lifecycle or what confirmation looks like. Adequate to start a call, incomplete for understanding consequences.

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 75% and already documents content, memory_id, and the visibility enum with omit-to-leave-unchanged semantics. The description adds a partial- versus full-update hint ('and/or') but says nothing about the undocumented `reason` parameter or valid enum values.

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 (update) and resource (a saved memory) plus the exact mutable fields (content and/or visibility) addressed by id. This separates it from remember_fact and forget_memory, though it does not name those siblings explicitly.

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 phrase 'Proposes only' hints that changes go through a proposal/confirmation flow, but the description never says when to use this versus remember_fact or forget_memory, nor how the proposal is later confirmed. An agent must infer the workflow from sibling names like confirm_change.

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