audit

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

No annotations are provided, so the description carries the full burden. It discloses that the tool only returns live nodes for stale/orphans and archived nodes for archived mode, and for stale mode it emphasizes never archiving autonomously. This provides critical behavioral context beyond the schema, though it omits specifics about how results are presented or pagination.

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 well-structured, starting with overall purpose then detailing each mode succinctly. Every sentence adds value, and it front-loads the core function. It achieves high information density without redundancy.

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 adequately explains return types for each mode. It covers parameter scoping and mode-specific behavior. However, it lacks details on result formatting, pagination, or handling large result sets, which are minor gaps for a comprehensive tool.

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?

With 100% schema coverage, baseline is 3, but the description adds significant value: it explains memory_id scopes to a 'depth-2 BFS neighbourhood', tags use OR semantics, and limit applies to stale mode. It also clarifies mode enum meanings and that memory_id is ignored for non-stale modes, going well beyond the schema descriptions.

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 audits memory health across three modes (stale, orphans, archived), explaining what each mode does. It distinguishes the tool from siblings like recall, search, and forget by focusing on inspection and presenting findings rather than direct retrieval or mutation.

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 provides explicit guidance for each mode: for stale, it instructs to ask user before archiving; for orphans, it suggests linking or forgetting; for archived, it notes this is the right tool when search returns nothing. It also clarifies scope with tags and memory_id, effectively telling the agent when to use this tool over alternatives.

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