mind_doctor

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

With no annotations, the description carries the full behavioral burden, and it does not meet it. 'Check' implies a read-only inspection, yet the schema exposes a 'fix' flag that presumably mutates or repairs state; the description never discloses that this tool can change data, nor what would be changed or whether it is reversible.

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?

Three words with no waste and the verb is front-loaded, so it is structurally fine. The problem is under-specification rather than verbosity — it is concise to the point of being uninformative.

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 annotations, no output schema, and an undocumented mutating parameter, the description should explain what is checked, what the result means, and what fix does. None of that is present, so an agent cannot invoke it confidently.

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 description coverage is 0% and the description says nothing about the single 'fix' parameter, whose boolean semantics are the most consequential part of the call. The description adds zero meaning beyond the schema, and the schema itself explains nothing, leaving a mutation switch entirely undocumented.

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 gives a verb ('Check') and a resource ('system health'), so the intent is broadly readable, but 'system' is undefined and it does not differentiate itself from siblings like mind_stats or mind_quarantine_list, which also inspect state. An agent cannot tell from the text what is actually being diagnosed.

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?

There is no when-to-use guidance, no mention of when to run this versus mind_stats, and no statement of prerequisites or cost. The existence of a repair mode is never hinted at, so the agent has no basis for choosing between a diagnostic and a corrective call.

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