Run maintenance

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

With no annotations provided, the description carries the full burden, and it delivers. It discloses destructive auto-deletion, archiving conditions, TTL defaults, embedding backfill, and explicitly states that roles never decay. It also reassures that calling it is safe anytime.

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?

The description is one dense but well-organized sentence that front-loads the action and then lists each behavior clearly. There is no filler, and every phrase contributes operational meaning.

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 parameterless maintenance tool with no annotations and no output schema, the description covers what happens, when it happens, configuration defaults, and safety. Nothing needed to invoke the tool 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?

The tool has zero parameters, so the schema carries no burden. The description adds useful configuration context by naming REMEMBRA_ARCHIVE_AFTER_DAYS and REMEMBRA_ARCHIVE_TTL_DAYS with defaults, which is more than baseline for an empty-schema tool.

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 states a specific action ('Run maintenance') and enumerates concrete operations: archive unused memories, auto-delete old archived memories, and backfill missing embeddings. This clearly differentiates it from the sibling list/forget/store/digest/search tools.

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 does not name alternatives, but it gives explicit timing guidance: 'Safe to call anytime.' Since this is a standalone maintenance operation rather than a choice among competing query/update tools, this contextual guidance is sufficient.

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