invalidate_decision

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

The description discloses key behavioral traits beyond annotations: the decision remains for historical queries, is excluded from active queries, mutates the decision store, and is idempotent. It also specifies the return shape. This adds meaningful context beyond the annotations.

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, each carrying useful information: the action, the historical/active distinction, the usage condition, and the return format. No filler or redundancy; the most important purpose is front-loaded.

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?

Given the absence of an output schema, the returned JSON is explicitly stated. The mutation, idempotency, and retention behavior are all covered. The tool's effect on the knowledge graph and query behavior is clear, making it complete for the agent to invoke correctly.

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%, so both id and valid_until are documented there. The description itself does not add much parameter-level meaning beyond the schema, but it correctly implies valid_until is part of the return object. Baseline of 3 is appropriate.

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The description uses a specific verb ('Mark as no longer valid'), names the resource ('decision'), and clearly defines the outcome: the decision stays in the knowledge graph for historical queries but is excluded from active queries. This differentiates it from siblings like remember_decision and query_decisions.

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?

Explicitly states when to use the tool: 'Use when a decision is superseded or reversed.' It does not name alternative tools or give when-not-to-use guidance, but the usage context is clear enough for an agent to select it correctly.

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