Metis — Run Maintenance

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

With no annotations at all, the description carries the full burden and does well: it explicitly guarantees idempotency, reversibility, that nothing is destroyed, and that no arbitrary command can be passed — the key safety facts for a maintenance/ops tool. It omits whether any operation is disruptive (e.g. whether restart-dashboard interrupts in-flight work) or how long operations take.

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 safety guarantee is front-loaded and the operation list is dense and useful rather than padded. The "Args:"/"Returns:" docstring scaffolding is slightly mechanical and the Returns block duplicates the output schema, but the content justifies most of the length.

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 single-parameter tool with an output schema, the description covers the two things that matter most: the complete operation vocabulary and the safety contract. Minor gaps remain around side effects of individual operations and whether any are long-running or blocking.

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 0% and the single `operation` parameter has no description and no enum constraint, so the description is the only source of allowed values — and it enumerates all seven with a one-line meaning each (status, restart-dashboard, scan-library, etc.). This is essential information found nowhere else.

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 ("Run a safe Metis maintenance operation") and enumerates the seven operations, so the agent knows exactly what the tool does. It does not, however, distinguish itself from siblings with overlapping operations such as scan_library, scan_news, index_library_pdfs, or metis_doctor.

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?

"For researchers working in a chat client, where there is no shell" gives a clear situational context for use, which is better than nothing. But it never says when to prefer this tool over the many siblings that perform the same actions (scan_news, scan_library, metis_doctor), leaving the agent to guess.

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