Mnemo - Persistent AI Memory

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

The description adds valuable behavioral context beyond annotations: it specifies what types of data to store (user preferences, decisions, etc.) and the 'search before recommending' guideline. However, with annotations already declaring destructiveHint=true and other behavioral traits, the description doesn't fully explain what 'destructive' means in this context (e.g., what gets permanently deleted) or address other behavioral aspects like rate limits or authentication needs.

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 appropriately concise with three sentences that each serve distinct purposes: stating the tool's nature and actions, providing usage guidelines, and directing to documentation. It's front-loaded with the core information. The final sentence about using the help tool could be considered slightly extraneous but serves a practical purpose.

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 tool's complexity (9 parameters, destructive operations, multiple actions) and the presence of an output schema (which reduces the need to describe return values), the description is moderately complete. It covers the tool's purpose and usage guidelines well but has significant gaps in parameter explanation and behavioral transparency that would help an agent use it correctly, especially for a tool with destructive capabilities.

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?

With 0% schema description coverage for 9 parameters, the description carries the full burden of explaining parameter semantics but provides almost no parameter-specific information. It mentions 'actions' which maps to the 'action' parameter, but doesn't explain what each action does, what 'content', 'query', 'memory_id', 'category', 'tags', 'limit', 'data', or 'mode' parameters are for, or how they relate to different actions.

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 this is a 'persistent memory store' with specific actions (add|search|list|update|delete|export|import|stats), providing a clear verb+resource combination. However, it doesn't explicitly distinguish this tool from its sibling 'config' tool, which might also store configuration data, so it misses full sibling differentiation.

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 explicit usage guidance: 'PROACTIVE: save user preferences, decisions, corrections, project conventions. Search before recommending.' This gives clear context about when to use it (for persistent storage of various user data) and a specific behavioral guideline. However, it doesn't mention when NOT to use it or explicitly compare it to the 'config' sibling tool.

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