Computer Selfcheck

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

With no annotations, the description carries the full disclosure burden and does the most important part: it makes clear this is a mutating operation that applies "automatic repairs" and returns a list of them, so the agent won't mistake it for a passive health check. It falls short of stating what the repairs change, whether they are reversible, or whether confirmation is needed.

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?

Two short sentences, front-loaded with the action and followed by the check list, with zero filler. Every clause (including the enumeration of subsystems) earns its place by telling the caller what will be inspected.

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, and the description still summarizes the return shape (per-subsystem status + repairs applied), which is sufficient for calling it. The remaining gap is that a repairing, state-changing tool with no annotations should say something about the safety or scope of those repairs.

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; baseline 4 applies. The listed subsystem names are not parameters but they usefully preview what the call covers.

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 phrase ("verify all server subsystems and FIX what it can") and then enumerates the concrete checks (heavy imports, audit log writability, capture, OCR engine load, screenshot scale, outbound gate). No sibling tool performs self-diagnosis or repair, so an agent can distinguish it from computer_screenshot/computer_review immediately.

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?

"Self-heal" and "FIX what it can" imply it should be called when the computer subsystem is suspected of malfunctioning or throwing errors, but the description never states that condition explicitly, nor does it name an alternative (e.g. computer_review for read-only inspection) or say when not to call it. Usage is inferable rather than stated.

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