memory_stats

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

Annotations already cover readOnly, idempotent, non-destructive. The description adds important behavioral context: the memory is shared across all connected AI tools, and the tool confirms domain names before writing (a scoping warning). However, it doesn't disclose the return format or whether it might be slow, but the sharedness and read-only confirmation are valuable additions beyond annotations.

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?

Three sentences, no filler. The first sentence front-loads the core functionality with specifics, the second adds the shared-memory context, and the third gives usage guidance. Every sentence carries weight.

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 zero parameters and a clear list of returned statistics, the description is nearly complete for an agent to call correctly. It lacks explicit mention of the output format (e.g., JSON shape), but the list of stats makes it inferable. The shared-memory note and read-only reassurance add confidentiality. Minor gap: it doesn't mention that this might return a lot of data or that it's a summary, but that's minor.

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 description's job is to clarify what the result covers. The description enumerates exactly what statistics are returned (count, episodes vs prototypes, learned associations, domains, average quality). Since there are no parameters to document, this is a high baseline: it fully sets expectations for the output.

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 states a specific verb ('Get an overview') and resource (stored memory: total count, episodes vs consolidated prototypes, learned associations, domains, average quality scores). It distinguishes from siblings by positioning itself as the orientation/overview tool, distinct from memory_list_recent or memory_read. The purpose is immediately clear and specific.

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 explicitly tells the agent when to use it: 'Use it to orient yourself, to confirm the exact domain name before writing to it, or when the user asks what you remember.' It also implicitly excludes it as a tool for reading specific memories (that would be memory_read) and for recent lists. This is clear, action-oriented guidance.

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