forget

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

With no annotations, the description carries the full burden. It does disclose what soft mode does ('drop from recall index, keep history'), but leaves 'purge' completely undefined — no statement that it is irreversible, what else is deleted, or what is returned. For a destructive mutation tool with zero annotation coverage this is a significant 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?

One sentence, front-loaded with the verb and resource, and the parenthetical efficiently encodes both modes with zero filler. It is terse rather than padded, though that terseness edges into under-specification.

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?

A two-parameter node-deletion tool with no annotations, no output schema, and 0% parameter coverage needs more than this. Nothing is said about reversibility of purge, error behavior for unknown node ids, or the effect on related history — all of which an agent must know before calling it.

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 0%, so the description must compensate. It does map the two branches to the behavior (soft / purge) and implies node_id selects the target, but it never states that purge is a boolean flag defaulting to false, nor gives any format or scoping for node_id. Partial compensation only.

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 (forget) and resource (a node), and splits it into two named modes (soft vs purge), which an agent can distinguish from siblings like recall/remember. It never names those siblings explicitly, so sibling differentiation is only implied by the semantics of the words.

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?

'soft (drop from recall index, keep history) or purge' implies which mode to pick but gives no rule for choosing between them in practice and no when-not guidance. It also does not state prerequisites (ownership/permissions) or warn that purge should be used sparingly.

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