(S)AGE

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 explains the tool's atomic operation (recall + store), the dynamic nature of domains, and the episodic memory-building behavior. However, it doesn't mention potential limitations like rate limits, error conditions, or what happens if the domain doesn't exist yet.

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 efficiently structured with zero wasted sentences. It front-loads the core instruction ('Call this EVERY turn'), explains the dual functionality, and provides practical guidance about domains and relevance decisions. Every sentence adds value to the agent's understanding.

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?

For a tool with no annotations and no output schema, the description does an excellent job explaining the tool's purpose, usage pattern, and behavioral characteristics. The main gap is the lack of information about return values or what the agent should expect after calling the tool, which would be helpful given the absence of an output schema.

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 schema description coverage is 100%, so the schema already documents all three parameters well. The description adds meaningful context by explaining that domains are dynamic and should be created based on topic, and that observations should capture 'essential insight' from the turn. This provides semantic guidance beyond the schema's technical descriptions.

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 dual purpose: (1) recall consensus-committed memories relevant to the current topic, and (2) store an observation about the current turn. It uses specific verbs ('recalls', 'stores') and distinguishes this from a 'context window dump', making it distinct from potential siblings like sage_recall or sage_remember.

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 states 'Call this EVERY turn' and provides clear guidance on when to use it (for per-conversation-turn memory cycles) and how to decide what's relevant based on conversation context. It also distinguishes this from non-turn-based alternatives by emphasizing its atomic, episodic nature.

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