memory_govern

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

With no annotations provided, the description carries the full burden. It discloses that the tool is 'User-authorized' and that retire is for 'whole-memory retirement after explicit user authorization,' implying destructive potential. However, it does not describe the behavioral effects of other actions beyond their names, leaving some transparency gaps for conflict resolution or workspace migration side effects.

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?

The description is two paragraphs and efficiently front-loads the core purpose, then provides usage constraints. The action list is necessary and each sentence adds value, but the repeated 'workspace' references in the action list and the trailing guidance make it slightly denser than ideal. Still, it is well-structured and has no filler.

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?

For a tool with 10 actions, no annotations, and 0% schema coverage, the description gives a solid overview: scope, actions, exclusions, authorization requirements, and a fallback to help. It does not detail every action's semantics or return values, but the output schema and the help action can cover that. Overall, it provides sufficient context for correct selection and basic invocation.

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 0%, so the description must compensate. It adds meaningful semantics to the 'action' parameter by listing all valid action values, but the 'data' parameter remains opaque. The guidance 'If unsure about fields, call action=help' partially mitigates this, but the data parameter structure and per-action fields are not explained, so compensation is incomplete.

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 opens with 'User-authorized Memory Arbiter governance' and lists specific actions (retire, resolve_conflict, confirm, etc.), making the tool's purpose unambiguous. It clearly differentiates from sibling tools by explicitly directing ordinary updates to memory(action='update'), establishing a distinct governance role.

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?

The description gives explicit when-to-use and when-not-to-use guidance: 'Use only for explicit governance decisions' and 'Do not use retire for ordinary updates... use memory(action="update") instead.' It also scopes retire to 'whole-memory retirement after explicit user authorization' and recommends calling action=help if unsure about fields, providing strong decision support.

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