Recall relevant memory

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

With no annotations present, the description carries the full burden. It discloses the retrieval mechanism ('MMR retrieval, not a text match') and states that it returns relevant memories, which is meaningful behavioral context beyond the simple verb 'search'. However, it does not explicitly say that the operation has no side effects or whether it reads from a persistent store, though this is strongly implied.

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 front-loaded with the core purpose. Each sentence contributes: when to call, why it differs from a simple keyword search, and a fallback policy. There is no redundant or filler content.

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 a single parameter and no output schema, the description is complete enough. It tells the agent when to use the tool, what retrieval algorithm to expect, and what the result will be ('relevant memories'). An agent can confidently invoke it without further clarification.

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% and the query parameter is simply described as 'What to recall.' The description adds useful semantic guidance: the query is not a literal text match, so conceptual or paraphrased queries are appropriate, and it suggests what kind of content to search for (past context, preferences, project history).

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 identifies a specific action ('recall') and resource ('what you already know'), and adds a distinguishing mechanism: 'MMR retrieval, not a text match.' This is sufficiently specific and distinct from sibling tools like memory_add and memory_forget.

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 provides explicit when-to-use guidance: 'Call this at the START of a session, and whenever the user refers to past context, their preferences, or the project history.' It also gives a default heuristic: 'If unsure whether you know something, search first.' This leaves little ambiguity about when to invoke it.

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