memory_stats

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

With no annotations, the description must carry the safety/behavior burden. It implies a pure read operation by describing 'vital signs' and statistics, but it never explicitly states that the tool does not modify memory. The listed metrics do add useful behavioral context about what the call reports.

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 compact and well-structured: a front-loaded summary label, the specific metrics, then two concrete use cases. Every sentence earns its place and there is no redundant filler.

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 no-parameter, output-schema-backed diagnostic stat list, the description covers the main invocation purposes and the categories of returned information. Additional details like time window or persistence would be nice, but the output schema can supply those where needed.

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 input schema leaves nothing to explain. The baseline for no parameters is 4, and the description appropriately emphasizes what the response/statistics reveal rather than parameters that do not exist.

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 clearly defines the tool as a memory-bank statistics reader: it lists the exact metrics returned (occupancy vs capacity, hit rates, true-drop count, totals). This distinguishes it from content-focused siblings like memory_search or memory_get and states the diagnostic role rather than simply restating the name.

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?

It gives explicit use cases: 'gauge how much has been remembered' and 'diagnose why retrieval feels off.' It does not name alternative tools or say when not to use it, but the context is clear enough for an agent to select this tool over the sibling lookup/management tools.

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