check_health

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

Discloses that fix=true auto-repairs but is agent-scoped and locked-safe, and that critical file-integrity findings are report-only. This adds context beyond the readOnlyHint=false annotation, though more detail on the 'locked-safe' mechanism could help.

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 dense but well-organized, with the primary action stated first, followed by a list of detected issues and usage details. It could be slightly more concise, but the structure supports quick comprehension.

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 (20-check registry, repair capability, three parameters), the description is remarkably complete. It lists what is detected, what is returned (storage stats, distributions), and how to invoke repairs or subset checks, with no apparent gaps.

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?

While schema coverage is 100%, the description adds valuable context: for fix it notes 'agent-scoped, locked-safe', for checks it references a constant for valid names, and for agent_id it clarifies default behavior. This meaningfully extends 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 checks memory database health, enumerates specific checks (contamination, duplicates, FTS integrity, etc.), and distinguishes it from sibling tools that perform CRUD or archival operations.

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?

Provides guidance on using the fix and checks parameters, mentions agent-scoped and locked-safe repairs, and indicates when to run a subset of checks. However, it does not explicitly contrast with alternatives like deep_check.

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