Metis — Metis Doctor

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

No annotations are provided, so the description carries the full burden; it clearly discloses the read-only, non-mutating nature ('without changing anything') and enumerates the diagnostic surface (OS, Python, integrations, scheduled tasks, data). It does not disclose runtime cost, network access, or failure behavior, but the key safety trait is explicit.

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 core action and the read-only guarantee, then a compact inventory of what is checked. The final sentence ('Tell the person the result in plain words') is useful output guidance but slightly extraneous to tool selection; the whole thing is still tight.

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?

An output schema exists, so return values need not be explained, and the description covers scope, safety, and the repair alternative. It could add what an unhealthy result looks like or whether scans are slow, but for a zero-parameter diagnostic it is substantially complete.

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 the baseline is 4. The description correctly implies a no-argument invocation and requires no parameter guidance.

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 and resource ('Check everything Metis needs on this computer') and immediately scopes the check with 'without changing anything'. It enumerates the exact areas inspected and names the sibling it is not: 'To also repair, use verify_install'. An agent can distinguish it from verify_install without opening either schema.

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?

Explicitly routes the agent: use this for the install doctor's report and use verify_install when repair is also needed. It does not state when-not-to-use or preconditions (e.g., first-run only), which keeps it short of a 5.

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