everything_health

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

With no annotations, the description carries the full burden and does well: it discloses the diagnostic categories returned and that 'each issue has a fix,' which tells the agent the output is actionable findings rather than raw metrics. It stops short of stating whether the tool is purely read-only or whether it applies any changes.

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?

Front-loaded with the purpose, then a compact parenthetical list of concrete misconfiguration patterns. The list is long but each item (double-indexed drive, network-folder monitoring, foreground rescans, unsaved index, 32-bit build) is specific and earns its place.

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 no-arg diagnostic with no annotations and no output schema, the description covers both what is checked and what the response looks like (issues with fixes). Only the read-only/mutating nature and any cost of running the check are left unstated.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter information is missing because no parameters exist.

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?

States a specific verb+resource ('Index health and configuration self-check') and enumerates exactly what is inspected: version, build, database state, indexed volumes/folders, database age, and misconfiguration patterns. It is clearly distinguishable from search/count/maintain siblings, though it never explicitly contrasts itself with everything_maintain.

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?

Usage is implied rather than stated: the mention of slow indexing, RAM bloat and freezes signals a troubleshooting context, but there is no explicit 'call this when X' or routing against everything_maintain. An agent can infer the diagnostic use case but gets no exclusions or alternatives.

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