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

Annotations already declare readOnlyHint=false and destructiveHint=true, but the description adds substantial context the annotations cannot: the choice is persisted as an ordinary, visible memory rather than a hidden setting, and it discloses the propose→confirm gate with concrete response fields (status='confirmation_required', action_id, plan_token) and the handoff to confirm_action. That is exactly the behavioral detail needed for a gated write.

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?

Front-loads the purpose, then the parameter trigger, then the storage model, then the confirmation mechanics — a sensible order with little waste. The internal ticket reference '(TZ-017 Part C)' is noise for an agent and is the main trimming candidate.

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 one-parameter gated write with no output schema, the definition covers what it changes, how it is stored, who can undo it, and the exact confirmation handshake the agent must follow. Nothing needed to call it 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% for the single required boolean, so the description must carry the meaning — and it does, defining enabled=false as disable and enabled=true as re-enable with a user-phrasing example. It stops short of stating what the default state is or what happens to already-shown suggestions, keeping it just below a 5.

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 and resource plus scope: 'Turn the assistant's proactive OrgLines-feature suggestions ON or OFF for this user.' An agent can distinguish this from generic settings siblings and from the memory tools it references, without opening the 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?

Gives explicit invocation triggers mapped to parameter values: 'Call with enabled=false when the user says something like stop suggesting features; enabled=true to re-enable.' It also points to recall_memory / forget_memory as the place the resulting setting lives, so the agent knows where to look afterwards.

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