memory_write

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

No annotations are provided, so the description must fully convey behavioral traits. It mentions automatic contradiction detection and superseding of old memories, but does not detail side effects, permissions, or what 'superseded' means in practice (e.g., deletion vs. archival).

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 three sentences long, front-loaded with the primary action, and avoids unnecessary details. It is efficient, but could potentially be more concise by combining the last two sentences.

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 high parameter count, lack of annotations, and absence of output schema, the description is insufficient. It does not cover return values, error handling, or the full scope of parameters, leaving significant gaps for the agent.

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?

The schema has 0% description coverage across 22 parameters, yet the description only clarifies the 'type' parameter (with the 'auto' value) and implicitly mentions 'content'. It fails to explain the majority of parameters such as 'embed', 'scope', 'title', 'metadata', etc., leaving the agent with little guidance.

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 that the tool creates a MemoryItem and optionally embeds it, with automatic contradiction detection and superseding of old memories. It distinguishes from siblings like memory_supersede by implying that writing automatically handles conflicts.

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 context for when to use, mentioning automatic contradiction detection and the 'auto' type for LLM categorization. However, it does not explicitly compare to alternative tools like memory_supersede or indicate when not to use this tool.

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