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

readOnlyHint=true already establishes the safety profile, and the description adds real behavioral context beyond it: private brains are filtered out, results span the whole account, and there are no domain/site_id scoping constraints. It also tells the agent to disclose when an answer draws on multiple brains, which is a non-obvious behavioral expectation. Minor gaps: no ordering or result-size expectations stated.

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 purpose and return fields, then usage, then the cross-brain caveat — a sensible order. The third paragraph's 'say so when it does' is an agent-behavior instruction that is useful but slightly outside the scope of a tool definition, making the entry a touch longer than strictly necessary.

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?

There is no output schema, so the description compensates by enumerating every returned field (id, name, description, aliases, status, note count, last compiled timestamp, visibility). Combined with the filtering note and the get_brain pointer, an agent has everything needed to call and interpret this tool correctly.

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?

With zero parameters the baseline is 4, and the description usefully preempts a likely error by stating 'no domain or site_id needed' and that brains are site-agnostic. Nothing further is required since there are no parameters to disambiguate.

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 ('List all brains accessible to the authenticated user') and immediately enumerates the returned fields, so the agent knows exactly what it gets. It also separates itself from the sibling get_brain by explaining that private brains are omitted here but readable there.

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 use case — matching description and aliases to resolve natural-language references like 'restaurant brain' — and names the alternative (get_brain) for private brains. It does not address other potential alternatives such as search or describe_tools, so it stops short of full when/when-not coverage.

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