recall

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

With no annotations, the description carries the behavioral burden. It discloses the MMR diversity reranking, the default lambda, that the top result remains the most relevant, and how to request pure relevance ordering. This is meaningful behavioral detail beyond a simple 'retrieve memories' statement.

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, followed by usage context and the key algorithmic nuance. Every sentence contributes information that helps an agent decide and invoke correctly, with no wasted words.

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 description covers the operation, the data source, when to use it, and the diversity behavior, while the schema fully documents all parameters. It does not explicitly describe the return format or contrast with siblings like knowledge_recall or find_similar, but this is not critical for a straightforward retrieval tool.

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 100%, so the baseline is 3. The description adds extra semantic value specifically for the diversity parameter, explaining the MMR behavior and the effect of passing 0, which goes beyond the schema's formula. Other parameters are adequately covered by the schema.

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 verb 'Retrieve' clearly identifies this as a read operation, and the resource 'memories relevant to a query or topic' is specific. It is easy to distinguish from siblings like remember (write) or memory_list (listing) because the description focuses on query-based retrieval from past sessions.

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 explicitly says 'Use this when you need context from past sessions,' giving a clear trigger condition. It does not name alternatives or provide explicit when-not-to-use guidance, but the usage context is strong enough to guide selection.

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