Compact memory store

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

Annotations already declare destructiveHint=true, so the agent knows this can destroy data. The description adds valuable context: 'Preview or apply' indicates a dry-run mode, and 'Applied runs create a backup' discloses a safety net. This goes beyond the annotations and helps the agent understand the risk profile.

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, front-loaded with the core action and scope, followed by the key safety detail. Every word earns its place.

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 tool with 4 parameters and no output schema, the description covers the main operations and the backup safety net. However, it doesn't explain the preview/apply flow in terms of the confirm parameter, nor what happens to the backup (where it goes, how to restore). Given the destructiveHint annotation, a bit more operational context would be warranted.

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. It does explain the high-level operations (dedupe, expired removal, retention, purging) which map to the parameters, but it doesn't clarify the meaning of 'confirm' (likely the apply switch) or 'retentionDays' semantics (e.g., 0 meaning no retention). The description adds some meaning but leaves the parameter details to inference.

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 verb ('Preview or apply') and a clear resource ('memory store'), and lists the exact operations: deduplication, expired-record removal, retention, and deleted-record purging. It distinguishes itself from siblings like delete_memory or purge_memory by framing this as a compaction operation, though it doesn't explicitly name a sibling.

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 implies usage: preview first, then apply with confirm. It also notes that applied runs create a backup, which hints at safety. However, it doesn't explicitly state when to use this tool versus alternatives like purge_memory, consolidate_memory, or delete_memory, nor does it state when not to use it.

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