remember

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

With no annotations, the description carries full burden. It explains key clustering, synonym handling, and parameter behaviors (namespace, ttl, related_to, source auto-stamping). It also mentions traceability to conversations. Missing details on error conditions or duplicate keys.

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 a single dense paragraph that packs substantial information. It is front-loaded with the main purpose and key concept. Though lengthy, every sentence adds value. Minor improvement would be breaking into sections.

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 no annotations and no output schema, the description provides extensive context on memory model, usage patterns, and parameter details. Missing explanation of key_types and behavior on key reuse, but overall quite comprehensive.

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 0%, so description compensates by explaining namespace, ttl_seconds, related_to, and source (auto-stamped). However, the key_types parameter is not mentioned, leaving a gap.

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 purpose: 'Save important information to memory.' It explains the concept of keys as search terms, which distinguishes it from sibling tools like forget, read_memory, and recall. The purpose is specific and actionable.

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 advises to first use recall() before creating new keys, and provides guidelines for key selection (3-6 diverse keys) and cross-lingual usage. However, it does not explicitly state when not to use this tool or compare it to remember_batch.

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