marm_compaction

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: apply marks source memories as compacted, discard leaves source memories untouched, and candidates include a 'ready-to-use prompt.' This is meaningful contextual information beyond the schema, though it does not mention all side effects or error conditions.

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 well-structured: a one-sentence purpose, a workflow arrow, and a bulleted action list. Every sentence provides useful information without redundancy or fluff.

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?

The tool has complexity (six actions, multiple parameters) and no output schema, so the description should clarify return values and expected behavior for each action. The workflow is explained, but the response/return format for actions like status or candidates is not described, leaving the user guessing about what data comes back. This is a significant omission for a stateful workflow.

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%, so the description must compensate. It explains action values (status, candidates, stage, etc.) and the candidate_id parameter in context. However, the summaries parameter is never explicitly described, leaving ambiguity about its structure and usage (likely for batch apply, but not stated). This is a noticeable gap.

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 sentence states the tool's exact purpose: 'Compact related memories into a single summary to reduce context bloat.' The verb (compact) and resource (memories) are clear, and the workflow action list distinguishes it from sibling tools like marm_log or marm_smart_recall.

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 clear workflow (status/candidates → stage → review → apply/discard) and tells the user to run status first. It gives context for each action but does not explicitly name alternative tools or state when not to use this tool, so it falls short of a 5.

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