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

Beyond the standard hints (readOnlyHint, idempotentHint), the description provides critical, non-obvious technical details such as the specific event types required for reading (27235) and writing (30420), and the data capacity limit (1 MB per key).

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?

Despite its density, the text is highly efficient. Every clause contributes vital information—be it cryptographic requirements, functional modes, or size limits—without any superfluous wording.

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 the complex, secure, and technical nature of the memory service, the definition is exceptionally complete. It dictates the required identity proof, capacity, and the exact conditions for use.

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?

Although schema coverage is 100%, the description is crucial here. It defines the expected content and purpose of the `key` (empty=list) and the `auth_event` (must be a specific signed event), adding necessary operational context beyond the data types provided 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 description clearly states the function (read/list) and the resource (encrypted memory entry). It distinguishes its dual purpose by specifying behavior when the key parameter is empty versus when it is provided.

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 is extremely explicit about prerequisites: the agent must prove the key using a specific NIP-98 event kind, including the required URI and time window. It also defines the full operational scope (read vs. list).

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