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

Annotations already flag destructiveHint=true and readOnlyHint=false, so safety is covered. The description adds genuinely new policy context: health and religion facts are refused, which tells the agent to expect a rejection on those topics. It omits what 'forget' destroys exactly and whether it is reversible.

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?

Four short sentences are front-loaded and there is no filler, but the telegraphic style ('Fact.', 'Drop.', 'Who.') borders on under-specification, and the dangling 'On which_person, ask' adds confusion rather than 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 7-parameter destructive mutation with no output schema, the description covers the refusal policy but says nothing about dry_run previewing, project scoping, or what a successful save versus forget returns. It is usable but leaves real gaps.

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%, so each parameter already carries a description and the baseline is 3. The description adds no meaning to kind, value, forget, dry_run, or project; its only parameter-like remark references 'which_person', which is not a real parameter name.

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?

Uses specific verbs ('Save or forget') with a specific resource ('a person fact') and explicitly bounds the domain ('Not events or payments'), which separates it from note/event/calendar siblings. The closing phrase 'On which_person, ask' is confusing because no such parameter exists in the schema.

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 clear negative guidance (not events or payments; health and religion refused), which implies when not to call it. It never names the read counterpart (connections_intel_about_person) or tells the agent to check existing facts before saving.

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