maintain

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose key aspects: it recomputes activation, reassigns tiers, and explicitly notes that items are placed in a review queue 'awaiting human sign-off before deletion', implying non-destructive immediate action. It does not mention potential side effects like performance impact or irreversibility, but for a zero-parameter trigger, it provides substantial behavioral context.

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 a single, well-structured sentence that front-loads the action and lists the specific steps and outputs. It is concise with no filler, and every clause adds necessary information: what the pass does, what it returns, and the key detail about human sign-off for deletion.

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?

Given the tool has no parameters and no output schema, the description must clarify what it returns. It states it returns 'the changes plus the tier-4 review queue', which is adequate, but it does not specify the format of the changes or queue items. However, for a zero-parameter operation with clear high-level behavior, this is reasonably complete. It could mention that the operation is safe to run repeatedly, but that is a minor gap.

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?

There are zero parameters, so the baseline is 4. The input schema is empty and schema coverage is 100% (no parameters to document). The description does not need to explain any parameters, and it does not introduce any confusion. A score of 4 is appropriate as the baseline for no-parameter tools.

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 verb ('Run the decay/archival pass') and explicitly lists the operations performed: recompute activation, reassign tiers, and return changes plus the review queue. This clearly distinguishes it from siblings like 'forget' (immediate deletion) and 'review_queue' (which likely only lists the queue without running the pass).

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 that this tool is used to trigger the archival pass, but provides no explicit guidance on when to call it (e.g., periodic maintenance) or how it compares to alternatives like 'forget' or 'review_queue'. It does not state when not to use it or mention specific exclusions. The purpose is clear, but the when-to-use context is left to inference.

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