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

With no annotations, the description carries full responsibility. It discloses the cost and embedding-based similarity, but omits behavioral details such as error handling, empty result behavior, or any rate limits. Basic behavior is clear but not fully transparent.

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 two sentences, front-loading the core purpose, and adds only essential details (cost, namespace). No wasted words or redundancy.

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 key purpose and cost, but with 2 parameters, no output schema, and zero annotations, it leaves gaps: no details on return format, query parameter semantics, or error cases. It is adequate for a simple tool but not complete.

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 50% (only k described). Description adds context that results are 'top-k' and paid, but does not explain the 'query' parameter beyond the tool's purpose. It partially compensates for the missing schema description but not fully.

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?

Description clearly states the tool performs semantic search over memories, specifying the namespace (payer-wallet) and return type (top-k by embedding similarity). It distinguishes itself from siblings (memory_export, memory_stats, memory_write) which cover other operations.

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?

Description implies usage for semantic retrieval of memories, and the sibling names clarify alternatives. However, it does not explicitly state when not to use this tool or provide context for choosing between searching and other operations.

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