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

Annotations already declare readOnlyHint true, idempotentHint true and openWorldHint false, so safety is covered. The description adds value beyond that by describing the response shape (summary, recent updates, source links, related memories) and a retrieval mode (shared memories via `from`), which annotations don't convey. No output schema exists, so this return-shape description is doing real work; only pagination/limit behaviour is missing.

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, front-loaded with the core action and followed by the usage scope and the alternate `from` mode. No filler, no restatement of the tool name.

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 6-parameter read tool with no output schema, the description covers the return payload, the natural-language query usage and the shared-memories alternative. It lacks detail on `hops`, `limit` and `detail` behaviour, but annotations carry the safety profile and the schema carries their definitions, so an agent can call it correctly.

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 83%, and the two parameters explained in prose (`from` for shared memories, plus the general retrieval scope) are already documented in the schema. `hops`, `brain`, `limit` and `detail` are not elaborated beyond their schema descriptions, so the description adds little beyond what structured data provides — baseline 3.

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 opens with a specific verb and resource — 'Answers a natural-language question from the user's brain' — and then enumerates the exact return payload: relevant memories, summary, recent updates, source links, related memories. That level of specificity distinguishes it clearly from memory_search and memory_get siblings (raw search / single fetch).

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?

It gives a concrete usage scope ('questions about the user's own people, projects, decisions and history') and explains the key alternative mode ('Optional `from` searches memories other people have shared with the user instead'). It doesn't explicitly say when NOT to use it in favour of memory_search, but the context is clear enough for an agent to pick correctly.

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