CPersona

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

The annotation indicates readOnlyHint=false, and the description appropriately discloses the write behavior by warning that setting fix=true will 'auto-repair' detected issues. It also lists the specific categories of problems detected and states that it 'Returns storage stats,' providing context about output despite the lack of an output schema.

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 efficiently structured across four sentences: purpose declaration with scope (15 checks), detailed enumeration of specific validations, return value disclosure, and operational instruction for the repair flag. Every sentence conveys concrete, non-redundant information without 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?

Given the tool's complexity (15 distinct health checks and auto-repair capability) and the absence of an output schema, the description adequately compensates by specifying that 'storage stats' are returned and detailing what health issues are detected. The readOnlyHint=false annotation is appropriately contextualized by the explicit 'auto-repair' disclosure, though it could further clarify what specific repair actions are taken.

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?

Input schema has 100% description coverage. The description reinforces the fix parameter's purpose with the phrase 'Set fix=true to auto-repair,' adding imperative usage context beyond the schema's declarative 'Auto-fix detected issues,' but does not add semantic details for agent_id beyond the schema's scope specification.

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 states a specific verb and resource ('Check memory database health') and enumerates nine distinct validation areas (contamination, duplicates, oversized content, etc.) that clearly distinguish this diagnostic tool from sibling CRUD operations like store, recall, or delete_memory.

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 operational guidance for the fix parameter ('Set fix=true to auto-repair'), explaining how to enable the repair mode. However, it lacks explicit guidance on when to invoke this diagnostic tool versus alternatives—for example, it does not indicate whether this should be run proactively, reactively to specific error symptoms, or on a schedule.

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