PruneMemory

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 clearly states the operation is a hard delete, defines the exact selection rule (max possible decay score below score_floor), and even translates the default into a time estimate (~115 days). It does not mention side effects like return counts, but the output schema covers return structure.

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 compact and front-loaded: the first sentence states the purpose, and the following lines explain the selection rule and parameter without redundancy. Every sentence earns its place, and the Args block is clearly formatted for quick scanning.

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 one-parameter tool with an output schema and no annotations, the description covers purpose, destructive behavior, selection criteria, and parameter semantics well. The only notable gap is explicit guidance on when to invoke this tool relative to sibling tools like Forget, but the core operational context is complete.

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 only gives type and default for score_floor, with 0% schema description coverage. The description fully compensates with a dedicated Args section explaining what score_floor controls, the default value, and how to adjust it for a more conservative prune. This exceeds what the schema provides.

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 opening phrase 'Hard-delete decayed and soft-deleted episodic memories' names a specific verb (hard-delete), a clear resource (episodic memories), and a precise scope (decayed and soft-deleted). This clearly distinguishes the operation from generic memory operations and from siblings like Recall or MemoryStats.

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 implies this is a maintenance/cleanup operation for removing decayed or already-soft-deleted rows, but it never explicitly states when to use PruneMemory versus alternatives such as Forget. There are no exclusions or routing hints to sibling tools, only parameter-tuning guidance ('Set lower to be more conservative').

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