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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds value by detailing the directional behavior: for a reflection ID it returns lower-tier memories, for a raw memory it returns reflections it was consolidated into. This goes beyond annotations without contradicting them.

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 (five sentences) with front-loaded usage guidance, a clear action statement, and a drill-down usage pattern. Every sentence earns its place with no redundancy or filler.

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 parameter and a known output schema, the description covers purpose, usage, behavioral details, and safety. It is complete without needing to describe return values since an output schema exists.

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%, providing a clear description for memory_id. The description repeats that the ID comes from a search result or previous inspect, but adds no new structural or semantic detail beyond what the schema already contains. Baseline 3 is appropriate.

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 explicitly states the tool inspects memory lineage by returning lower-tier memories or reflections based on a memory ID. It clearly distinguishes itself from sibling tools like search_memories (searching) and delete_memories (deleting) through its specific verb and resource.

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 explicit when-to-use guidance: 'Use this when the user asks why the assistant believes something, or wants to see the source memories behind a reflection.' It also suggests using repeatedly to drill down. It does not explicitly state when not to use, but sibling context implies alternatives exist.

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