Remember

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

Annotations already flag this as a non-readonly, non-idempotent, open-world write. The description adds genuinely useful context beyond that: writes are scoped to the authenticated user, gated by opt-in and tenant policy, and near-duplicates are auto-suppressed. It does not describe the response or failure modes (e.g. policy rejection), leaving a small gap.

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 sentence that front-loads the when-to-use gating and then packs in behavior. No filler, nothing redundant with the schema or title.

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 intent, target, auth scope, policy gating, and dedup behavior, which is nearly everything an agent needs. It omits what the call returns and whether the suppression is reported, a minor but real gap.

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% for both parameters, including the kind enum and the 4000-char limit, so the schema carries the parameter burden. The description adds no additional meaning beyond 'fact,' so the baseline 3 applies.

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 names a specific action and target: 'persist a fact' into 'the authenticated user's memory.' It is clearly distinguishable from the read-side sibling bee_memory_search, though it never names that sibling explicitly to reinforce the contrast.

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?

'Use only when the user intends Bee to persist a fact for future conversations' is an explicit gating condition with an intent-based trigger, which is stronger than most. It does not name the alternative tool (bee_memory_search) or state when NOT to add, so it stops short of a 5.

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