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

Beyond the destructiveHint and idempotentHint annotations, the description discloses the proposal/apply safety model, tombstone deletions that persist across devices, the use of the same typed writers, and the model-call cost. This is rich behavioral context with no contradiction against the annotations.

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 dense sentences, front-loaded with the core purpose and followed by the invocation pattern, safety guarantees, and cost. Every clause adds necessary information; there is no filler or redundancy.

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 single-parameter destructive tool with no output schema, the description explains what the proposal contains, what applying means, and the side-effect guarantees. An agent has everything needed to invoke it safely and predict the outcome.

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?

The schema already covers confirm with a short description, so the baseline is met. The description adds meaningful procedural semantics: omitting confirm produces a proposal, while confirm:true applies the changes, which is helpful for correct invocation.

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 names a specific action ('Clean up and consolidate the workspace Memory') and the resource, with explicit criteria: dropping product-behavior entries, phone numbers, emails, and merging near-duplicates. This clearly distinguishes it from related memory tools like list_memory, remember, and forget.

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 description explicitly prescribes a two-step workflow: call with no argument to get a proposal, then call again with confirm:true to apply it. It clearly states that nothing changes in proposal mode, though it does not name alternative tools or exclusion conditions.

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