NocturnusAI

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it's a maintenance operation that expires facts based on TTL and evicts low-salience facts when memory exceeds capacity, implying it's a write operation that modifies memory state. However, it doesn't specify side effects like whether evicted facts are permanently lost or if there are rate limits.

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 concise and well-structured, with two sentences that directly address purpose and usage without unnecessary details. Every sentence adds value: the first explains what the tool does, and the second provides critical usage guidance, making it front-loaded and efficient.

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 tool's complexity (a maintenance operation with memory management) and no annotations or output schema, the description is mostly complete. It covers the tool's purpose, behavior, and usage context, but lacks details on output format or error handling, which could be helpful for an agent invoking it.

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?

The input schema has 100% description coverage, with the 'threshold' parameter fully documented in the schema. The description does not add any parameter-specific information beyond what the schema provides, such as default values or usage examples. Baseline 3 is appropriate since the schema handles parameter documentation adequately.

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's purpose with specific verbs ('Run memory decay and eviction') and resources ('facts'), distinguishing it from siblings by focusing on memory management rather than querying or asserting facts. It explicitly mentions expiring facts past TTL and evicting low-salience facts, which differentiates it from tools like 'delete_scope' or '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?

The description provides explicit guidance on when to use this tool: 'Call periodically in long-running agent sessions to prevent unbounded memory growth.' This gives clear context for usage versus alternatives, such as using it for maintenance rather than for querying (like 'recall') or modifying facts (like 'tell').

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