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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds real behavioral context: retracted layers are excluded by default and only surface as an audit trail when requested, plus a note that certain flags reduce the payload.

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?

Two sentences, zero filler, with the primary return contract front-loaded and the filtering caveat second. Every clause carries 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?

For a read-only single-item getter with no output schema, the description supplies exactly the missing piece: what the response contains. Annotations handle safety and the schema handles parameters, so nothing an agent needs is absent.

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 100%, so all six parameters are already documented, including retracted's default and lastLayers' bounds. The description's synthesis that lastLayers/section/bodyOnly 'return less' adds a little framing but no syntax or semantics beyond the schema.

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?

States a specific verb and resource ('Returns one memory') and enumerates the returned content (body, dated update layers, links, source references). The singular scope distinguishes it cleanly from memory_list, memory_search and recall without needing their schemas.

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 implies when the optional parameters apply (retracted off by default; lastLayers/section/bodyOnly narrow output), but it never says when to choose memory_get over memory_search, recall, or memory_list. Usage is inferable rather than stated.

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