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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, but the description adds material context they cannot: an account-bound computer:write OAuth requirement and possible local owner approval prompts for what is nominally a read. The only gap is that it never hints at the shape of the returned preference values, which matters since no output schema exists.

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 short clauses, front-loaded with the capability, then the alternative, then the exclusion, then the auth constraint. Every sentence carries distinct information and nothing is repeated from annotations.

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 zero-argument read tool, the description covers scope, the mutating counterpart, exclusions, and authorization prerequisites. The only shortfall is the absence of any indication of what the returned preference object looks like, which an agent would otherwise have to discover at call time.

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?

Zero parameters, so there is nothing for the description to disambiguate; the tool is called with an empty object. Baseline 4 applies, and the description correctly avoids inventing filtering options.

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 (read) plus the exact resource and its bounded scope: 'EXZA search depth/result preferences' only. It also immediately names the sibling that changes them, so an agent can distinguish get from set without opening either schema.

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?

Explicitly routes the agent: use this to read, use exza_set_commander_preferences to modify. It adds a negative boundary as well ('no security settings are exposed'), so the agent knows this tool will not answer security-config questions.

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