memory_forget

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them by quantifying exactly what is destroyed: records >180d never recalled with low confidence are archived, >365d archived records are purged, and the action log is pruned past TAM_ACTION_LOG_RETENTION_DAYS. It does not state whether archived records remain recoverable or what the dry-run output looks like.

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?

One front-loaded sentence listing the three retention actions in order of aggressiveness, followed by a four-word rationale. No filler, and the destructive scope is stated before the justification.

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 maintenance tool with no output schema, the description supplies the eligibility rules, the thresholds, and the configurable retention window, which is enough to call it correctly. Missing only what the call returns (counts of affected records) and whether archival is reversible.

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 single parameter dry_run has 100% schema description coverage ('If true, only show what would be affected'), so the schema fully carries the semantics. The description never mentions dry_run, adding no meaning beyond the structured field; baseline 3 applies.

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 ('Apply retention policy') plus three concrete sub-actions (archive, purge, prune) with thresholds, so the agent knows exactly what the tool does. It doesn't explicitly name a sibling such as memory_delete to contrast against, which keeps it short of a 5.

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?

'Keeps memory clean' implies a periodic maintenance use case, and the thresholds imply when records become eligible. However, there is no explicit statement of when to call this versus memory_delete (targeted deletion) or memory_consolidate, and no prerequisites or exclusions are given.

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