mem_save

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

With no annotations provided, the description carries the full burden. It discloses the upsert behavior for topic_key ('update in-place') and implies memory persistence. However, it doesn't mention potential side effects like overwriting existing memories, auth requirements, or rate limits. It's a write operation but doesn't explicitly state that it mutates state, though that's implied. This is adequate but not rich.

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?

Front-loaded with 'Save memory' and organized with a clear structure (bullet points for observation content, then topic_key guidance). Every sentence is informative and earns its place. Slightly longer than strictly necessary but efficient; no filler.

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?

The tool has 8 parameters, but no output schema (so no return value to explain). The description covers the main usage patterns (different kinds, structured observation template, topic_key upserting) and complements the schema. It doesn't explain every parameter (e.g., scope, type, title) but those are self-explanatory in the schema. For the complexity involved, it's sufficient and complete enough.

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% for parameters, so baseline is 3. The description adds value by explaining the structured content format (What/Why/Learned) for observations, clarifying the default for kind, and explaining topic_key's role in updates. This goes beyond the schema's basic descriptions of each parameter, particularly for content and topic_key.

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 'Save memory' and enumerates the four write modes (observation, prompt, session summary, passive learning), distinguishing it from sibling read tools like mem_recall, mem_get, and mem_context. It uses a specific verb (save) with a clear resource (memory) and outlines the different content types, making it unambiguous.

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?

Provides explicit guidance on when to use kind=observation with structured content and when to use topic_key for evolving topics. It implies that other kinds are for different contexts (prompts, session summaries, passive learning) but doesn't explicitly state when not to use the tool or contrast with read alternatives. Still, the context is clear enough for an agent to select appropriately.

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