brain_doctor

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

With no annotations, the description carries the full burden and does disclose the two important traits: default behavior is read-only inspection, and fix=True performs repairs but only 'what is safe', signaling partial rather than wholesale mutation. It omits runtime cost, whether repairs are reversible, and any permission requirements.

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 sentences, no filler. The inspection scope is front-loaded and the mode switch plus usage trigger follow in the second sentence.

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 described, and the description covers what it inspects, its modes, and when to invoke it. The remaining gap is operational: no sense of how long a full vault scan takes or how disruptive fix mode can be.

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 single parameter has 0% schema description coverage, but the description compensates by explaining fix=True explicitly enables repair while the default is check-only. That is the essential semantic an agent needs for this boolean.

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 the vault for problems) and enumerates the exact problem classes it detects: broken links, missing notes, failed videos, stale creators. The added fix mode and the pointer to search/status failures distinguish it cleanly from siblings like brain_status and search_brain.

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?

Gives a concrete trigger: run it when search looks wrong or status shows failures, which implicitly routes the agent away from search_brain/brain_status toward this tool when those surface errors. It does not state when-not to use it or name the alternatives explicitly, so it stops short of full routing guidance.

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