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

Annotations already cover read-only, idempotent, non-destructive behavior, so the description's job is to add context — and it does, disclosing the one-minute staleness window and the fact that this is a directory flag rather than a live media presence signal. That is exactly the kind of caveat annotations cannot express.

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 behavior and immediately followed by the limitation. Nothing is wasted and nothing is buried.

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 simple read tool with full annotation coverage, the caveats are the main missing piece and they are present. However, with no output schema, the description should indicate what the flag actually returns (a boolean value, an object, an availability enum), and it never addresses the only input parameter.

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%, so the single parameter expertId is documented nowhere; the description never mentions it, its format, or where it comes from. It should have compensated for the schema gap rather than relying on the parameter name being self-explanatory.

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 ('reads the directory availability flag') and adds a negative boundary ('not a live media presence check') that separates it from presence-style tools. It stops short of naming the closest sibling, get_expert_availability, so the distinction from that tool must be inferred.

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?

The staleness caveat ('up to a minute old') implies when the result is acceptable and when the caller needs something fresher, but no alternative tool is named. With get_expert_availability in the sibling list, the description should say which one to prefer in which case.

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