marm_compaction

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

No annotations are provided, so the description carries full burden. It explains each action's behavior, including that 'apply' marks source memories as compacted and 'discard' leaves them untouched. No contradiction with annotations since none exist.

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 well-structured with a workflow line and bullet-pointed actions. It is not overly long, but some phrasing could be tightened. Every sentence adds value.

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 no annotations, output schema, and low schema coverage, the description adequately covers the tool's behavior and usage pattern. It explains the workflow step by step. Missing details like return values or error handling, but sufficient for a multi-action tool.

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%. The description adds meaning by explaining what each action expects (e.g., for 'stage', it mentions candidate_id and suggested_summary). However, it doesn't fully map to the schema fields (summaries, candidate_id) or describe the array structure of summaries.

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 the tool's purpose: compact related memories into a single summary to reduce context bloat. It lists all possible actions, distinguishing it from siblings like marm_summary and marm_delete.

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 provides a workflow (status/candidates → stage → review → apply/discard) and explicitly says to run 'status' first. It doesn't explicitly exclude scenarios, but the usage guidance is clear. No sibling alternatives mentioned, but the tool's unique purpose suffices.

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