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

No annotations exist, so the description carries the full burden, and it does disclose the important state model: the decision 'stays in history but is flagged in traces', i.e. a soft invalidation rather than a hard delete. It omits any statement about permissions, reversibility, or what happens when a title prefix matches multiple decisions.

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 dense sentences, zero filler. The core action comes first, followed by persistence behavior and matching semantics; every clause adds information an agent needs.

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 no explanation, and the mutation's soft-delete behavior is disclosed. The notable remaining gap is ambiguity handling for prefix matching and whether an invalidated decision can be restored.

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%: workspace and superseded_by are described in the schema, but the required 'decision' parameter is undocumented there. The description compensates by explaining the matching semantics ('matches by decision title prefix') and the optional supersede recording, which is genuine meaning beyond the raw 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States a specific verb+resource: mark a decision invalidated/superseded, with a parenthetical example of the triggering scenario. It is distinguishable from the many sibling read tools (wyrm_decision_trace, wyrm_decision_upstream) and from wyrm_truth_set, though it does not explicitly name a sibling it overlaps with.

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?

Gives a clear triggering context — 'e.g. a ground truth it rested on changed' — which tells the agent when this tool applies. There is no explicit when-not guidance or named alternative (e.g. recording a new decision via wyrm_remember instead), so it falls 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.