memory_consolidate

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

With no annotations, the description carries the full behavioral burden, and it does disclose one non-obvious trait: pruning is opt-in and off by default via an environment variable. However, it never says whether dedup merges or deletes records, whether the operation is reversible, or whether the score boosts are persistent mutations.

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?

A single sentence front-loads the two default behaviors and defers the opt-in destructive one to a parenthetical. No filler, no restatement of the tool name.

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 zero-parameter maintenance mutation with no annotations and no output schema, the description covers what happens but not the surrounding context an agent needs: expected frequency, safety/reversibility, or what the operation reports back. Adequate but with clear gaps.

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 schema has nothing to document and the baseline is 4. The description does add one quasi-parameter detail by naming the KB_PRUNE environment variable that toggles the prune behavior.

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 names three specific operations on a specific resource: deduplicating near-identical memories, boosting frequently-used ones, and pruning stale ones. That is a concrete verb+resource statement that separates it from siblings like memory_remember, memory_recall, and memory_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 only conditional given is operational ('enable with env KB_PRUNE=1'), which tells the agent when pruning happens but not when to invoke consolidation at all. There is no guidance on triggers (e.g., after bulk ingest, periodically) or when to prefer memory_forget for targeted deletion instead.

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