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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavior beyond that: duplicate facts are skipped rather than accumulated, and entities are found-or-created and linked into a knowledge graph. It stops short of stating auth requirements or what identifier is returned.

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?

A single dense paragraph, front-loaded with the action and the trigger condition before the selectivity caveats and field guidance. Slightly long, but nearly every clause carries a distinct instruction (selectivity, standalone wording, entity coverage, dedup), so little is wasted.

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 mutation tool with no output schema, the description covers purpose, trigger conditions, exclusions, dedup behavior, and key field expectations. It could go one step further and say what a successful save returns, but an agent has what it needs to call this 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 description coverage is 100%, so the baseline is 3, but the description adds genuine semantics: `fact` must be concrete and standalone so it reads correctly months later, and `entities` should enumerate every person/company/product/project/tool/topic so the graph links them. That is more than restating 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 ('Save a NEW memory') plus the destination ('user's cloud brain') and timing ('immediately'). This cleanly separates it from read-side siblings like recall_memories, search, and get_memory_source.

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?

Explicit about when to use it (durable reusable facts: decisions and reasoning, preferences, changed facts about people/companies/products/projects/tools, goals, constraints) and when not to (transient chatter, one-off task mechanics, secrets, anything already saved). Nothing is left to inference.

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