check_health

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

Beyond the readOnlyHint=false annotation, the description discloses many behavioral traits: lossy/irreversible repairs, report-only file-integrity findings, per-run caps, the remaining convergence signal, unknown-check rejection, and the removal of the old healthy boolean. This is exactly the side-effect and edge-case disclosure an agent needs.

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 long but dense and front-loaded: the core purpose and check list come first, followed by repair caveats and status semantics. Each sentence carries distinct information; the historical note about the removed healthy boolean is useful but adds length that could be trimmed in a more tightly structured definition.

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?

For a tool with no output schema and only one annotation, the description covers behavior, return signals (status, issues, severity_summary, checks_run, remaining, storage stats), version nuances, and parameter usage. An agent has enough information to invoke it correctly and interpret results, including convergence behavior.

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% (all parameters described), but the description adds meaning beyond the schema: it explains that fix=true is agent-scoped, lossy/irreversible, and capped, and that checks rejects unknown names rather than silently doing nothing. It does not add details for agent_id or session_key beyond their schema descriptions, so a 4 is earned rather than a 5.

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 opens with a specific verb and resource — 'Check memory database health' — and enumerates 29 named check categories, making the scope unusually concrete. However, it never names or contrasts sibling tools such as deep_check, so it stops short of explicit sibling differentiation.

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?

It gives clear operational guidance: use checks to run a subset, set fix=true to auto-repair, and re-run until remaining stops decreasing. It does not explicitly state when to prefer this tool over alternatives like deep_check, but the context strongly implies a health/safety-check role.

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