gc

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

With no annotations, the description carries the behavioral burden and explains the important knobs: dry_run previews, archive_instead selects archiving over deletion, and limit bounds processing. It documents return values and error behavior, though it does not explicitly warn that setting dry_run=false permanently deletes memories.

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 purpose is front-loaded, and the Args/Returns/Raises structure is compact and free of filler. Every sentence adds useful information.

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?

Since there is no output schema, the description correctly provides the exact return keys and the ValueError condition. The inclusion of dry_run, archive_instead, and limit behavior makes the tool callable without needing external documentation.

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 description coverage is 0%, and the Args section fully compensates by adding a meaningful one-line explanation for each parameter, including the valid limit range of 1-10,000.

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 states a specific verb and resource: 'Remove or archive low-scoring memories.' This clearly distinguishes the tool from sibling search, analysis, and consolidation operations, despite the cryptic name 'gc'.

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 first line implies the tool is for low-scoring memory cleanup, but it never explicitly says when to prefer this over sibling tools such as consolidate_memories or promote_memory, and it provides no when-not-to-use guidance.

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