Consolidate memory

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

Annotations only say destructiveHint=true and idempotentHint=false; the description goes well beyond by scoping the deletion precisely (working-memory slots with relevance <= 0.01 are removed, that is the ONLY deletion, long-term memory is untouched) and clarifying dedup behavior ('once, however often the pass runs'). This is exactly the context needed to trust a destructive-hinted tool.

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?

Front-loaded with the action and mechanism, and every clause carries information (thresholds, deletion scope, timing). Slightly run-on across three long sentences, but there is no filler to cut.

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?

With an output schema present, return values need not be explained, and annotations cover the safety profile. The description supplies everything else an agent needs: trigger timing, thresholds, exact deletion scope, and a verification workflow via zenbrain_health.

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 tool takes zero parameters, so the baseline of 4 applies. The description instead documents implicit inputs (the 100 most recent episodes, the 0.5 weight threshold, the 0.01 relevance cutoff) that would otherwise be invisible to the caller.

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 first clause gives a specific verb (run a consolidation pass) and resource (memory), then immediately defines the mechanism: recent episodes with emotional weight > 0.5 become semantic facts. An agent can distinguish this from zenbrain_store/recall/health without opening any schema.

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?

Explicit when-to-use ('between sessions or after a batch of zenbrain_store calls'), explicit when-not ('not on every turn'), and it recommends comparing zenbrain_health before and after. Both the trigger condition and the sibling to use for verification are named.

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