Extract memories from conversation

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

The description discloses key behavioral aspects: extracted items default to pending (anti-poisoning), fallback to rule mode without external calls, and idempotence is implied by the annotation. No contradictions with the idempotentHint annotation.

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 concise, using two sentences to cover functionality, usage timing, and default behavior. It avoids unnecessary fluff while retaining all essential information, making it easy to parse.

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 the full schema coverage and the presence of an output schema (not shown but indicated), the description provides sufficient context for correct invocation. It includes when to call, fallback handling, and default state, leaving no critical 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?

All three parameters (scope, messages, sessionId) have descriptive metadata in the schema. The description also explains the default scope and the chronological nature of messages, enhancing understanding beyond the schema alone.

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 the tool's function: feeding recent conversation messages to the engine for automatic memory extraction. It distinguishes modes (LLM or rule) and is unambiguous about its purpose relative to other memory-related tools.

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?

Explicitly provides when to call the tool (at conversation wrap-up or when enough dialogue accumulates) and instructs not to wait for a host hook. It also mentions fallback behavior to rule mode when LLM is unavailable, giving clear operational guidance.

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