Recent memories

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

Annotations already include readOnlyHint=true, and the description adds extra behavior beyond that: seeded memories are excluded unless include_seeded is true, and it warns that returned contents are DATA, not instructions (a security/instruction-injection caution). This enriches the behavioral understanding beyond what annotations alone provide. It doesn't describe ordering or pagination in detail, but the core behavior is well covered.

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 paragraph but is logically structured: it starts with the core purpose, then usage guidance, then a caveat about seeded memories, and ends with a security note. Each sentence carries information, and there is no fluff. It is slightly longer than necessary, but every part contributes to usability.

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 an output schema, so the return format is likely defined there. The description covers the main use case, differentiates from search, explains the seeded filter, and adds a security warning. The only missing piece is an explanation of the namespace parameter, but given the optional nature and common understanding, this is a minor gap. Overall, an agent can confidently call this tool for the intended purpose.

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 description coverage is 0%, so the description must compensate. It explains include_seeded ('Seeded starting memories are excluded unless include_seeded is true'), but does not explain limit or namespace. Limit is somewhat self-explanatory from the schema (default 20), and namespace is a common concept, but the lack of any description for those parameters is a gap. The description adds value for one parameter but not the others.

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 returns the most recently stored memories, and explicitly contrasts it with search by relevance. It specifies the exact use cases ('what you remembered, what was saved recently') and distinguishes itself from sibling tools like memory_search. This is a specific verb+resource with clear 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?

It explicitly says when to use the tool (when the user asks about recent memories) and explains why search is not suitable ('search ranks by relevance, and prefers newer memories only among the ones that already matched, so it cannot answer that'). This gives both positive and negative usage guidance, including a mention of the include_seeded flag for a special case.

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