recall

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses a meaningful dependency ('requires embedding API') and explains the fusion mechanism (BM25 + semantic + tag graph → RRF), which adds context beyond the schema. However, it does not mention output shape, pagination, error behavior, or any side effects/read-only guarantees, leaving gaps for an agent to discover at runtime.

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 compact and scannable, front-loading the tool's purpose in one line and then using a tight bullet list for each mode. Every line adds useful information with no filler.

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?

This is a complex multi-mode tool with 9 parameters, no annotations, and no output schema. The description gives helpful mode summaries and key dependency warnings, but does not fully specify required parameters per mode (e.g., what 'similar' and 'fuse' require), limit behavior, or return value expectations. An agent can likely call it, but some trial and error is still needed.

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 does explain several parameter families (date/from/to, daysAgo/monthsAgo/yearsAgo, semantic similarity) in relation to modes. However, it does not describe 'limit', 'text' explicitly, or how parameters combine for the 'fuse' mode, so parameter semantics remain incomplete.

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 performs 'multi-mode memory retrieval' and enumerates four distinct retrieval modes with specific meanings. It identifies the resource (memories) and the operation (retrieve/fetch/find), making the purpose clear. It does not explicitly contrast itself with sibling tools like search_memories, so it stops short of full 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 gives per-mode usage guidance: day uses date or from+to, timemachine uses relative time, similar requires an embedding API, and fuse is described as best for finding specific things. It provides a clear context for choosing among modes, though it does not address when to use recall versus sibling tools such as search_memories or read_memories.

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