remember

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

In the absence of annotations, the description reveals key behavioral traits: it records a trace and deterministically chooses create vs append based on matching strength. This adds value beyond the schema. However, it doesn't detail side effects like overwrites or permission 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 a single, front-loaded sentence with no superfluous content. It efficiently conveys the core purpose and key behavior.

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?

Despite high parameter count and complexity, the description is brief. It explains the auto-merge logic but lacks details on return values (though output schema exists), error cases, or parameter interactions. Given the richness of the schema, the description could be more complete.

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%, so baseline is 3. The description does not add meaning beyond the schema parameter descriptions. It mentions 'records a trace' but does not clarify how parameters like mode or meta affect behavior.

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: it's an agent-friendly write API that records a trace and deterministically decides to create a new memory or append to a strongly matching existing memory. This distinguishes it from siblings like create_memory (always creates) or append_memory (always appends).

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 does not explicitly guide when to use this tool vs alternatives. It omits when-not-to-use or prerequisites. The term 'agent-friendly' hints at ease of use, but no concrete scenarios or exclusions are provided.

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