memory

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

The description discloses actions like archive, hydrate, and update_importance, implying mutability, which aligns with readOnlyHint=false. It also adds version info for chain_head and history. However, it does not disclose side effects, prerequisites, or error conditions. Annotations provide no additional safety hints beyond false flags, so the description adds moderate value.

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 structured as a list of actions with inline explanations, which is functional but verbose. It front-loads the overall purpose but then repeats 'v0.8.0' and 'v0.8.0+' unnecessarily. Could be more concise by grouping common behaviors.

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 10 parameters, no schema descriptions, and many siblings, the description lacks key context. It doesn't explain return values despite an output schema existing (not shown). The distinction between 'list' and 'search' is unclear, and filtering capabilities are not described. The description leaves significant gaps for correct tool selection and invocation.

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 0%, so the description must compensate. It only explains two parameters (namespace for chain_head, rid for history) out of ten. Other parameters like limit, offset, sort_by, domain, importance, memory_type, text_contains are left unexplained. The action-specific context (e.g., 'rid' needed for get) is implicit but not explicit.

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 purpose as managing individual memories and lists specific actions like get, list, search, etc. This is specific enough to distinguish from broad categories, though it does not explicitly differentiate from sibling tools like recall or remember.

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 lists available actions but provides no guidance on when to use this tool versus alternatives. For example, it does not explain when to use memory's 'list' versus a sibling's 'recall'. Only chain_head and history have brief usage notes, but overall no when-to-use or when-not-to-use context.

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