nmem_auto

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

No annotations are provided, so the description carries the full disclosure burden. It does reveal that 'process' saves (mutation) and that 'flush' is an emergency capture skipping dedup with a lower threshold, but says nothing about what gets overwritten, idempotency, or permission requirements for a write-capable tool.

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 tight sentences, action semantics front-loaded before the usage note. Minor redundancy with the action enum descriptions, but no filler or preamble.

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 mutation-capable tool with no annotations and no output schema, the description covers triggers and the two key actions but omits what the caller gets back and the safety profile. Adequate as a minimum viable entry point, with clear gaps.

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 coverage is 100%, so all five parameters including the action enum are already documented in the schema, and the description's enum glosses largely restate it. Baseline 3 applies; the description adds little parameter meaning beyond the schema.

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+resource: auto-extract memories from text, and sketches the two most consequential actions ('process'=analyze+save, 'flush'=emergency capture). It does not differentiate itself from close siblings like nmem_remember or nmem_remember_batch, so the agent cannot fully tell which entry point to prefer.

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 concrete context: 'Use at session end or when processing large text blocks,' and ties 'flush' to the pre-compaction emergency case. It offers no explicit exclusions (e.g., when to fall back to nmem_remember instead), so the routing is implied rather than closed.

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