mem_save

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

With no annotations, the description carries full burden. It discloses that topic_key causes in-place updates (upsert) and provides structured content format, but does not explain persistence guarantees, potential data loss, or error scenarios. This is adequate but not comprehensive.

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: two paragraphs plus a structured format block. It front-loads the primary purpose, and every sentence adds value without redundancy.

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 complexity (8 parameters, no output schema, no annotations), the description covers main use cases but lacks return value details, error handling, and side effects. The structured observation format is helpful, but overall completeness is moderate.

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 parameters are described in the schema (100% coverage), so baseline is 3. The description adds value by specifying structured content for observations (What/Why/Where/Learned) and explaining topic_key for upserts, going beyond schema descriptions.

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 explicitly states 'Save memory' and lists the supported kinds (observation, prompt, session_summary, passive_learnings), making it clear it is the write tool. It distinguishes itself from siblings by calling itself 'this single write tool', implying other siblings are for reading.

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 provides guidance on when to use different kinds (e.g., durable observations use kind=observation with structured content, topic_key for evolving topics). It does not explicitly compare to sibling tools, but its self-identification as the write tool makes usage context clear.

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