kernel_facts_retract

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

With no annotations, the description carries the full burden, and it does disclose one important trait: retraction is non-destructive because the fact remains in history. It says nothing about authorisation, whether a retraction can be reversed, idempotency, or what happens when the id does not exist — all material for a mutation tool.

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 tight sentences, front-loaded with the semantic distinction and closing with the history-retention property, so every clause earns its place. The extreme terseness borders on cryptic for an agent unfamiliar with the fact model, but nothing 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?

An output schema exists, so return values need not be described, and the tool is conceptually simple. Still, for an unannotated mutation the description should address the unidentified required `id` and the failure/undo story, neither of which is covered.

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 67%; the description reinforces the meaning of `how` (ended vs wrong) and ties `at` to the moment truth ceased, adding a little framing beyond the enum descriptions. However, `id` — the sole required parameter — is never explained in either the description or the schema, leaving the most important input undocumented.

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 conveys a specific semantic action: invalidating a fact, either as having ended at a point in time or as never having been true. The final clause, 'It stays in the history,' distinguishes this from a hard delete, which is the crucial differentiation. It never explicitly names the counterpart tool (e.g., kernel_facts_assert), so sibling routing is implied by the name rather than stated.

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?

Usage is only implied through the how values: pick 'ended' for a fact true until `at`, 'wrong' for one that was never true. There is no explicit statement of when to call this versus asserting a new fact or querying as-of a date, and no prerequisites or error conditions are given.

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