Prune / consolidate memory

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

Adds significant behavioral detail beyond annotations: explains that unused memories are cooled and cold ones collapsed to a trace (still searchable, never deleted). Annotations already indicate non-destructive and idempotent nature, and the description reinforces and elaborates on these traits.

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?

Two concise paragraphs: first explains the process in detail, second describes arguments and return value. No unnecessary words. Highly 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 single parameter (fully documented), no output schema needed (description mentions return type), and the clear explanation of the consolidation process, the description is complete for an agent to understand usage and behavior.

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 single parameter dry_run is fully described in the schema (100% coverage). The description repeats the same info verbatim, adding no additional semantics. Baseline score of 3 is appropriate.

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?

Clearly states the action (run consolidation pass), the resource (memory tiers), and the specific operations (recompute, cool, collapse). Distinguishes itself from siblings like mindmap_forget by emphasizing that nothing is destroyed.

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?

Implies usage as a manual trigger for the automatic consolidation background thread, but does not explicitly state when to use this tool versus alternatives like mindmap_forget or mindmap_tidy. Lacks direct guidance on selection criteria.

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