marm_compaction

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

With no annotations, the description fully discloses behaviors: each action's effect is described (e.g., apply commits a staged summary and marks source memories compacted, discard rejects without touching sources). This goes beyond minimal safety cues.

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 concise with a clear workflow overview and bullet-pointed actions. Every sentence adds value, and the structure aids quick comprehension.

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 the tool's multi-step complexity and no annotations, the description covers the workflow, action semantics, and side effects (compacted marking). Since an output schema exists, the absence of return value details is acceptable.

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 0%, but the description explains the 'action' parameter and mentions 'candidate_id' and 'suggested_summary' for stage. However, the 'summaries' parameter is not explained, and the optional 'source_memory_ids' mentioned in the description is not in the schema, causing incomplete mapping.

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 specific actions (status, candidates, stage, review, apply, discard) with distinct purposes, distinguishing it from siblings like marm_summary.

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 advises running 'status' first. However, it does not explicitly state when to use this tool versus alternatives or when not to use it.

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