govern_memory

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

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses that actions are auditable and that raw archive data is never deleted. However, it doesn't fully clarify the reversibility or side effects of the mutations (e.g., whether 'delete' is a hard delete or soft delete, or whether audit events are always written).

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 three sentences, front-loaded with the core purpose, then the critical usage caveats. Every sentence earns its place with actionable information, and there is no fluff or repetition.

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 tool's complexity (8 params, multiple actions) and no output schema, the description provides the essential guidance for safe usage (dry-run, confirmation, reason). It lacks details about return values or what happens after each action, but the schema covers parameter specifics. Overall, it is sufficiently complete for an agent to select and invoke the tool 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?

The schema already provides 100% coverage for all 8 parameters with descriptions. The tool description adds strategic usage context (e.g., dry_run first, confirm_destructive requirement) but doesn't introduce new parameter semantics beyond the schema. Thus, the 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 clearly states the tool's function with specific verbs ('delete, reject, or mark curated memories stale') and a specific resource ('curated memories'). This distinguishes it from sibling tools like save_memory and search, which serve different purposes.

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 concrete usage guidance: 'Use dry_run=true first to preview affected IDs' and 'Non-dry-run mutations require confirm_destructive=true and an explicit reason.' This is actionable and explains when to take precautions, though it doesn't explicitly compare to alternatives among sibling tools.

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