memory_stats

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

Adds real behavioral context beyond readOnlyHint: it warns that counts may be zero-filled placeholders when metrics collection is disabled and tells the agent to read the 'measured' flag to disambiguate. That is exactly the kind of non-obvious trait an agent could otherwise misinterpret as a genuinely empty store.

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 sentences, no waste. The primary return content is front-loaded and the caveat follows immediately, so the agent reads the important behavior without scanning.

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?

An output schema exists, so return shape needn't be explained, and the description covers the one piece of behavior the output schema cannot convey on its own — that zeros may mean 'not measured' rather than 'empty'.

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 takes zero parameters, so the schema baseline of 4 applies; there is nothing for the description to compensate for.

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 and resource ('Return aggregate statistics about the memory store') and enumerates what's included: thought count, edge count, storage size. This clearly distinguishes it from all siblings, which are per-item or listing operations (get_thought, list_memory, search_memory).

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?

Gives a clear context for use (inspecting aggregate store size/counts) and specifically calls out the disabled-metrics scenario where the numbers are placeholders. It stops short of explicitly naming alternatives, but the sibling set contains no equivalent stats tool, so the routing ambiguity is low.

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