invalidate_decision

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

Annotations declare idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds that it mutates the decision store (aligning with readOnlyHint=false), returns JSON with specific fields, and idempotent behavior. It does not contradict annotations, and adds meaningful context about what gets invalidated and return format.

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?

Three sentences: states action, explains consequence, provides usage context and mutability, mentions idempotence and return format. No wasted words, every sentence adds value.

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 no output schema, the description includes the return format. It covers all necessary behavioral aspects for an agent to use the tool correctly. No missing information given the tool's complexity and the richness of annotations.

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 baseline is 3. The description explains both parameters: id (decision ID) and valid_until (ISO timestamp, default now). It adds meaning beyond the schema by clarifying the purpose of valid_until and its default value.

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 clearly states the tool marks a decision as invalid, explains it remains in the knowledge graph for history but is excluded from active queries, and specifies usage context (superseded or reversed). This distinguishes it from siblings like approve_decision or reject_decision.

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 advises to use when a decision is superseded or reversed. While no explicit when-not is given, the context is clear from the description and sibling names. Could be improved by stating not to use for permanent deletion, but sufficient.

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