vault_hygiene_scan

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

With no annotations, the description fully discloses behavior: read-only, never rewrites or deletes, produces suggestions to act upon. It explains key terms like 'confidence flapping' and states it is 'report-only', providing complete transparency.

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 concise yet comprehensive: one paragraph for purpose and behavior, a clear constraint sentence, and a parameter list. It front-loads the main action and uses bullet-point-style readability.

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 (scanning beliefs for multiple hygiene issues), the description covers all necessary aspects: purpose, what it detects, non-destructive nature, and parameter details. The output schema is present but not shown, so return value explanation is not needed.

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?

Although input schema description coverage is 0%, the description includes an 'Args' section that explains both parameters (contradiction_threshold and max_age_days) with defaults and what they control, fully compensating for the lack of 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 uses specific verbs like 'Scan', 'report-only', and lists concrete actions (contradiction detection, merge suggestions, staleness flags, confidence flapping). It clearly distinguishes from write tools by stating 'Never rewrites or deletes a belief'.

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 explains the tool is for 'report-only living-context maintenance' and explicitly states it does not modify data, implying use for diagnostics. However, it does not directly compare to sibling tools like refresh_beliefs or vault_write_action.

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