review

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

With no annotations, the description carries the full disclosure burden, and it does reveal the real behavioral trait that matters: exactly which classes of memory become candidates. However, for a tool whose name and phrasing ('tidy up') hint at mutation, it never says the operation is non-destructive, nor whether stale_days filtering is applied as a strict cutoff or a sorting hint.

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 short sentences with zero filler, and the criteria are front-loaded before the usage hint. The first sentence is a telegraphic fragment, which is dense but slightly less immediately parseable than a full clause would be.

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?

The presence of an output schema means return values need not be described, and the one-parameter surface is simple. Still, for a review-and-remediate workflow with no annotations, the description should state that nothing is modified and point to the deletion tool, otherwise an agent may mistake 'tidy up' for an action.

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% for the single parameter, so the description must compensate, and it partially does by tying stale_days to the 'unused for' staleness criterion. It does not address the 180-day default, the unit of measure, or whether the threshold is inclusive, so the gap is only partly closed.

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The description identifies the resource (memories) and the precise selection criteria — unused for stale_days, superseded, or repeatedly saved — which is far more specific than the bare name 'review'. It never states an explicit verb (returns? lists? deletes?), so the agent must infer that this is a reporting pass rather than a mutation, which keeps it from 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?

"Use when the user asks to clean up memory" gives a clear triggering context. It stops short of explicit exclusions or naming the sibling 'forget' as the step that actually deletes, so the agent must reason about the handoff on its own.

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