memory_decay

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

With no annotations, the description fully discloses it removes memories based on a decay model and mentions the dryRun parameter for safe preview. It does not detail permanence of deletion or side effects, but the behavioral intent is clear.

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 sentences: first defines the tool's function, second provides usage guidance. No redundant information, front-loaded, and 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?

For a simple tool with one boolean param and no output schema, the description covers purpose and usage adequately. It could mention return format (e.g., count of removed items) but is complete enough for its complexity.

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?

Schema coverage is 100% and the dryRun parameter is well-described in the schema. The description adds no extra meaning beyond the schema's 'report without deleting'.

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The description clearly states it runs an intelligent forgetting engine that removes low-quality, outdated memories using a Weibull decay model. This distinguishes it from sibling tools like memory_delete (manual) and memory_forget (specific forgetting), as it automates cleanup based on a decay model.

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 advises calling periodically (e.g., once per session) to keep memory clean, providing clear timing guidance. However, it does not specify when not to use it or directly compare to alternatives like memory_bulk_delete.

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