audit

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

With no annotations provided, the description fully discloses behavioral traits: it explains return types (e.g., conflicts returns object with candidates and truncated), side effects (none for read modes, but warns against autonomous archiving), and constraints (e.g., excluded pairs for conflicts, only live nodes for most modes). This exceeds expectations.

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 with clear sections for each mode and key behavioral rules. However, some phrases are repeated (e.g., the note about cross-domain drift), and the level of detail could be slightly tightened without losing meaning. Overall, it is appropriately sized and 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 description provides adequate detail on return formats for some modes (e.g., conflicts), though other modes only say 'Return memories' without specifying structure. The description covers the essential context for the tool's four modes and usage, making it mostly complete.

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 each parameter is already documented. The description adds valuable context beyond the schema, such as the effect of omitting domain (scans entire workspace) and that memory_id applies only to stale mode. This extra information enhances understanding, justifying a score above baseline 3.

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 that the tool inspects the health of knowledge across four distinct modes (stale, orphans, archived, conflicts). It specifies the verb (inspect/audit) and the resource (knowledge in a domain or workspace), and distinguishes itself from sibling tools by focusing on auditing and maintenance tasks.

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 on when to use each mode and what actions to avoid (e.g., 'Never archive autonomously' for stale mode, 'Never auto-file contradicts edges' for conflicts). It also suggests follow-up actions using sibling tools like connect and forget, and clarifies scope (entire workspace vs. specific domain).

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